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. 36329
    Prev
    Next
    INDEX
    Explanations

    transform origin/anchor

    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
     провод
    -0.07
     ZIP
    -0.07
     Mold
    -0.07
     Hann
    -0.07
     clearance
    -0.07
     Hindered
    -0.06
    _legacy
    -0.06
    _)
    ↵
    -0.06
    [U
    -0.06
     withstand
    -0.06
    POSITIVE LOGITS
    chunks
    0.07
    ANCEL
    0.07
     apache
    0.06
    OMP
    0.06
    `),↵
    0.06
    rup
    0.06
     '!
    0.06
     Eating
    0.06
    omens
    0.06
    Frozen
    0.06
    Activations Density 0.007%

    No Known Activations