© 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. 7-RESID-POST-AA
    11. 55530
    Prev
    Next
    INDEX
    Explanations

    Sports tournaments/standings

    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
     breakout
    -0.07
     suction
    -0.06
     default
    -0.06
     Vendor
    -0.06
    AR
    -0.06
    (course
    -0.06
    -source
    -0.06
    stm
    -0.06
     suburban
    -0.06
    ivalent
    -0.06
    POSITIVE LOGITS
     которого
    0.07
     которую
    0.07
     якого
    0.07
    .shopping
    0.07
     metres
    0.06
    очку
    0.06
     приготов
    0.06
    кость
    0.06
     púb
    0.06
    _LOADED
    0.06
    Activations Density 0.015%

    No Known Activations