Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7-RESID-POST-AA
    6. 93500
    Prev
    Next
    INDEX
    Explanations

    ological

    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
    (..
    -0.06
    ACHINE
    -0.06
    .timer
    -0.06
    Continuous
    -0.06
     -*
    -0.06
     فصل
    -0.06
    ']*
    -0.05
     taps
    -0.05
    뉴스
    -0.05
     علی
    -0.05
    POSITIVE LOGITS
     morphology
    0.11
     MOR
    0.07
    million
    0.07
     minib
    0.07
    たち
    0.07
     behavior
    0.07
     doorstep
    0.07
     prefers
    0.07
    /apt
    0.07
    osta
    0.07
    Activations Density 0.003%

    No Known Activations