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. 7-RESID-POST-AA
    6. 93017
    Prev
    Next
    INDEX
    Explanations

    amic

    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
     Utf
    -0.06
    ones
    -0.06
    _/
    -0.06
    bpp
    -0.06
    etre
    -0.06
    otas
    -0.06
    LineEdit
    -0.06
    neys
    -0.06
    ndef
    -0.06
     sg
    -0.06
    POSITIVE LOGITS
     aiding
    0.07
    ...');↵
    0.07
    '+↵
    0.07
    ми
    0.07
    \GeneratedValue
    0.06
    '];?>↵
    0.06
     gadget
    0.06
     RESULT
    0.06
    .getFloat
    0.06
     emotionally
    0.06
    Activations Density 0.002%

    No Known Activations