Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 81452
    Prev
    Next
    INDEX
    Explanations

    story beginnings

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on words that begin new sentences or blocks of text (especially capitalized first words and “NAME_” placeholders).

    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
    [pos
    -0.07
    _IMP
    -0.07
    ROSS
    -0.06
    _ROW
    -0.06
    وزه
    -0.06
    亿
    -0.06
    $value
    -0.06
    TEXT
    -0.06
    Global
    -0.06
    gettext
    -0.06
    POSITIVE LOGITS
     bez
    0.07
     zám
    0.06
    >';↵
    0.06
     киш
    0.06
    (dec
    0.06
    -Jan
    0.06
     orbits
    0.06
    .crt
    0.06
     voll
    0.06
     Sandbox
    0.06
    Activations Density 0.052%

    No Known Activations