© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 19261
    Prev
    Next
    INDEX
    Explanations

    cancer research

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _Pl
    -0.07
    .serial
    -0.07
    _theme
    -0.07
     Proj
    -0.07
    xfff
    -0.06
    dart
    -0.06
    processing
    -0.06
    _And
    -0.06
     declines
    -0.06
     reviewer
    -0.06
    POSITIVE LOGITS
    ushima
    0.06
    52
    0.06
    炉
    0.06
     Kumar
    0.06
    (hour
    0.06
    (opcode
    0.06
    .parseLong
    0.06
    (reinterpret
    0.06
     Cassandra
    0.06
    过来
    0.06
    Activations Density 0.016%

    No Known Activations