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. 85358
    Prev
    Next
    INDEX
    Explanations

    file paths, code

    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
     одерж
    -0.06
    ,-
    -0.06
     }}">↵
    -0.06
    ('');↵↵
    -0.06
     sẵn
    -0.06
    crime
    -0.06
     σας
    -0.06
    _rgb
    -0.06
    ステ
    -0.06
    _CAST
    -0.06
    POSITIVE LOGITS
     Recon
    0.06
     Pretty
    0.06
     trademarks
    0.06
    работ
    0.06
     vacuum
    0.06
     Relay
    0.06
     seit
    0.06
     Decay
    0.06
    dez
    0.06
    忽
    0.06
    Activations Density 0.001%

    No Known Activations