© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 17956
    Prev
    Next
    INDEX
    Explanations

    prob

    np_max-act · gemini-2.0-flash
    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
     bids
    -0.07
    bcm
    -0.06
    iot
    -0.06
    рах
    -0.06
     muse
    -0.06
    存在
    -0.06
     bidding
    -0.06
    ических
    -0.06
    (effect
    -0.06
     評価
    -0.06
    POSITIVE LOGITS
    GestureRecognizer
    0.07
    754
    0.06
    @GeneratedValue
    0.06
    停止
    0.06
    loub
    0.06
    abay
    0.06
     beneath
    0.06
    尋
    0.06
     strikeouts
    0.06
    _construct
    0.06
    Activations Density 0.001%

    No Known Activations