© 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. 80059
    Prev
    Next
    INDEX
    Explanations

    boolean logic

    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
    .card
    -0.07
    uelve
    -0.07
     unique
    -0.06
    GIN
    -0.06
    留
    -0.06
    .button
    -0.06
     Buffy
    -0.06
    家庭
    -0.06
    ギ
    -0.06
    柄
    -0.06
    POSITIVE LOGITS
    &s
    0.07
     inflater
    0.06
     sonuç
    0.06
     Artifact
    0.06
    ElapsedTime
    0.06
    >';
    0.06
    \system
    0.06
    /compiler
    0.06
     vex
    0.06
    Hist
    0.06
    Activations Density 0.085%

    No Known Activations