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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 9162
    Prev
    Next
    INDEX
    Explanations

    especially

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ik
    -0.07
    [ip
    -0.07
    (schedule
    -0.07
    Such
    -0.07
    _ent
    -0.06
    AndPassword
    -0.06
    unds
    -0.06
     hex
    -0.06
    Urls
    -0.06
     Dec
    -0.06
    POSITIVE LOGITS
    레스
    0.07
    �a
    0.07
    ária
    0.06
    /job
    0.06
    ív
    0.06
     الشي
    0.06
    rijk
    0.06
     niche
    0.06
    iliyor
    0.06
    _seed
    0.06
    Activations Density 0.031%

    No Known Activations