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. 59465
    Prev
    Next
    INDEX
    Explanations

    suggest

    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
    elim
    -0.06
    :#
    -0.06
    xd
    -0.06
     Frag
    -0.06
    '}}>
    -0.06
     쇼
    -0.06
     robotics
    -0.06
     practiced
    -0.06
    selection
    -0.06
     Simulation
    -0.06
    POSITIVE LOGITS
     İstanbul
    0.07
    Queryable
    0.06
     bildir
    0.06
    .intent
    0.06
    TO
    0.06
    reira
    0.06
    ظˆ
    0.06
    失
    0.06
     ал
    0.06
    抽
    0.06
    Activations Density 0.074%

    No Known Activations