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. 9838
    Prev
    Next
    INDEX
    Explanations

    caregivers

    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
     martial
    -0.07
    (Test
    -0.06
     bol
    -0.06
    ponsors
    -0.06
     checksum
    -0.06
    HAM
    -0.06
    /pass
    -0.06
     charity
    -0.06
     flattened
    -0.06
    bras
    -0.06
    POSITIVE LOGITS
    िप
    0.07
    ServiceProvider
    0.07
    jug
    0.06
     IndexError
    0.06
    -operator
    0.06
    resp
    0.06
    _Blue
    0.06
    rapy
    0.06
     작업
    0.06
    ToolStrip
    0.06
    Activations Density 0.489%

    No Known Activations