© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41376
    Prev
    Next
    INDEX
    Explanations

    awful

    np_max-act · gemini-2.0-flash

    uncommon or surprising word pairings.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    This neuron activates on open-class content words (nouns, verbs, adjectives, adverbs) in natural-language text, while remaining silent on code tokens and function words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about teamwork and resilience in the face of adversity.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DAO
    -0.06
     RESET
    -0.06
    hq
    -0.06
    ti
    -0.06
     société
    -0.06
    REV
    -0.06
    (vc
    -0.06
    !=(
    -0.06
     ApiService
    -0.06
     AUTH
    -0.06
    POSITIVE LOGITS
    apped
    0.07
     Full
    0.07
     našich
    0.06
    Other
    0.06
     nového
    0.06
     تلفن
    0.06
    оряд
    0.06
    -standard
    0.06
    pread
    0.06
     forty
    0.06
    Activations Density 0.493%

    No Known Activations