© 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
    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. 92059
    Prev
    Next
    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash

    This neuron detects the standard forum permission notices about posting, replying, or deleting (e.g., “You cannot post new topics,” “You cannot reply,” “You cannot delete your posts”).

    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
    .capitalize
    -0.07
    .Username
    -0.07
    .'&
    -0.07
    scopy
    -0.07
    RowIndex
    -0.07
     utilis
    -0.07
     trunc
    -0.06
     مراجع
    -0.06
    幕
    -0.06
    525
    -0.06
    POSITIVE LOGITS
    >↵↵
    0.06
     bl
    0.06
     &&↵
    0.06
    _PAD
    0.06
     front
    0.06
     πο
    0.06
    ))];↵
    0.06
     tease
    0.06
     ロ
    0.06
    BT
    0.06
    Activations Density 0.000%

    No Known Activations