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. 60659
    Prev
    Next
    INDEX
    Explanations

    record

    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
    剛
    -0.07
    ANG
    -0.07
     Aynı
    -0.06
    477
    -0.06
    _te
    -0.06
    JSGlobalScope
    -0.06
    ’il
    -0.06
    От
    -0.06
    cleanup
    -0.06
    ubo
    -0.06
    POSITIVE LOGITS
     record
    0.07
    istics
    0.07
    ologické
    0.07
     prev
    0.07
     diffs
    0.06
     promotion
    0.06
     examination
    0.06
    ordination
    0.06
     order
    0.06
    _examples
    0.06
    Activations Density 0.005%

    No Known Activations