© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 59188
    Prev
    Next
    INDEX
    Explanations

    code or numerical data

    np_max-act · gemini-2.0-flash

    statements or questions about calculating counts/totals or indexing occurrences (e.g., number of items, siblings, or cumulative time) in programming/data contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    _MEDIA
    -0.08
     şiddet
    -0.07
    aisy
    -0.07
    (UINT
    -0.07
    ض
    -0.06
    yas
    -0.06
     coincidence
    -0.06
     normalization
    -0.06
     κυ
    -0.06
    rparr
    -0.06
    POSITIVE LOGITS
    anganese
    0.07
     registros
    0.07
    ROUT
    0.06
    irector
    0.06
    CellStyle
    0.06
    PLAYER
    0.06
     Panasonic
    0.06
     |[
    0.06
    _PROFILE
    0.06
     amend
    0.06
    Activations Density 1.309%

    No Known Activations