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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91732
    Prev
    Next
    INDEX
    Explanations

    financial news

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to common function words (e.g. prepositions, conjunctions, and determiners) rather than content words.

    oai_token-act-pair · o4-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
    补
    -0.07
    ins
    -0.06
     Nova
    -0.06
     rhythms
    -0.06
     افر
    -0.06
    awa
    -0.06
    outil
    -0.06
    adians
    -0.06
     Igor
    -0.06
     Gle
    -0.06
    POSITIVE LOGITS
    -acre
    0.07
    <algorithm
    0.06
     skl
    0.06
     трансп
    0.06
     +%
    0.06
    /apt
    0.06
     aplik
    0.06
     Với
    0.06
    .colorbar
    0.06
    飞
    0.06
    Activations Density 0.041%

    No Known Activations