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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 99500
    Prev
    Next
    INDEX
    Explanations

    конкрет

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aniem
    -0.07
    -slider
    -0.07
     surveillance
    -0.07
    创建
    -0.07
    vi
    -0.06
     municipalities
    -0.06
    QueryString
    -0.06
     militia
    -0.06
    flows
    -0.06
    Ev
    -0.06
    POSITIVE LOGITS
     ؟
    0.07
     hk
    0.07
     ontvangst
    0.06
     japanese
    0.06
     Prompt
    0.06
    teborg
    0.06
    (cn
    0.06
     लगत
    0.06
     تازه
    0.06
     arsch
    0.06
    Activations Density 0.010%

    No Known Activations