© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 90582
    Prev
    Next
    INDEX
    Explanations

    cost and weight

    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
    OTTOM
    -0.07
    Leader
    -0.07
     damaged
    -0.07
    ̈
    -0.07
    PGA
    -0.06
    Deaths
    -0.06
     δεδο
    -0.06
    ir
    -0.06
    mall
    -0.06
    лы
    -0.06
    POSITIVE LOGITS
     Olympus
    0.07
     핵
    0.06
    مد
    0.06
     fiss
    0.06
     mou
    0.06
     snap
    0.06
    933
    0.06
     kb
    0.06
    -have
    0.06
    .github
    0.06
    Activations Density 0.011%

    No Known Activations