© 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. 104769
    Prev
    Next
    INDEX
    Explanations

    Self-publishing

    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
    返回
    -0.07
    OUNCE
    -0.06
    ometer
    -0.06
     afternoon
    -0.06
    iye
    -0.06
    .configuration
    -0.06
     Channel
    -0.06
    	begin
    -0.06
    InternalServerError
    -0.06
    らない
    -0.06
    POSITIVE LOGITS
     displays
    0.07
    uminium
    0.07
    olum
    0.06
    _pemb
    0.06
    TRY
    0.06
     Italy
    0.06
    Mor
    0.06
     iter
    0.06
    Sell
    0.06
     změn
    0.06
    Activations Density 0.041%

    No Known Activations