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. 15-RESID-POST-AA
    6. 31077
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Budget
    -0.06
    ,当
    -0.06
     soll
    -0.06
    dddd
    -0.06
    Budget
    -0.06
    732
    -0.06
    _Search
    -0.06
     safest
    -0.06
     orchest
    -0.06
     лютого
    -0.06
    POSITIVE LOGITS
    색
    0.07
    itled
    0.06
     Thing
    0.06
    toUpperCase
    0.06
     info
    0.06
     mieux
    0.06
    ��
    0.06
    .Exception
    0.06
    .shiro
    0.06
     Lightning
    0.06
    Activations Density 0.000%

    No Known Activations