© 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. 68382
    Prev
    Next
    INDEX
    Explanations

    narrative text

    np_max-act · gemini-2.0-flash

    expressions of familial relationships and bonding experiences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect common function‐word and subword fragments (auxiliaries, pronouns, negations, question words, etc.) in narrative text.

    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
    230
    -0.06
    алізації
    -0.06
    गल
    -0.06
    023
    -0.06
     witty
    -0.06
     donated
    -0.06
     lety
    -0.06
     vivo
    -0.06
     хочу
    -0.06
     Stories
    -0.06
    POSITIVE LOGITS
     *)↵↵
    0.06
    .web
    0.06
    .unlock
    0.06
    ीर
    0.06
    Pred
    0.06
     �
    0.06
     answering
    0.06
    commons
    0.06
    _Insert
    0.06
    .matcher
    0.05
    Activations Density 0.224%

    No Known Activations