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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 60335
    Prev
    Next
    INDEX
    Explanations

    (c

    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
     Grund
    -0.07
     awful
    -0.06
    nickname
    -0.06
     Plaintiff
    -0.06
     bowls
    -0.06
    とい
    -0.06
     bad
    -0.06
    _lstm
    -0.06
     STOP
    -0.06
     Getter
    -0.06
    POSITIVE LOGITS
     tỷ
    0.06
    getContext
    0.06
    _mtx
    0.06
    -describedby
    0.06
    ‌توان
    0.06
    /share
    0.06
     accessToken
    0.06
     Millions
    0.06
     odak
    0.06
    asionally
    0.06
    Activations Density 0.002%

    No Known Activations