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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 9869
    Prev
    Next
    INDEX
    Explanations

    tryptophan

    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
    Indexes
    -0.07
     ListTile
    -0.06
    QB
    -0.06
    _Y
    -0.06
    .headers
    -0.06
     чор
    -0.06
    Item
    -0.06
    */
    ↵
    -0.06
     PyTuple
    -0.06
     Charges
    -0.06
    POSITIVE LOGITS
    (gr
    0.08
     وضعیت
    0.07
     absent
    0.06
    .warning
    0.06
    (Route
    0.06
    造成
    0.06
    asctime
    0.06
    armac
    0.06
     absence
    0.06
    Low
    0.06
    Activations Density 0.003%

    No Known Activations