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. 15-RESID-POST-AA
    6. 94663
    Prev
    Next
    INDEX
    Explanations

    output

    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
     thẩm
    -0.06
     unbiased
    -0.06
     течение
    -0.06
    .EOF
    -0.06
    [indexPath
    -0.06
     seeks
    -0.06
     ponds
    -0.06
    posure
    -0.06
     ballistic
    -0.06
    .isValid
    -0.06
    POSITIVE LOGITS
     руках
    0.07
    '}),↵
    0.07
     mobs
    0.07
    dur
    0.06
     Fou
    0.06
    crew
    0.06
    apple
    0.06
     Gle
    0.06
    ':[
    0.06
     смерти
    0.06
    Activations Density 0.019%

    No Known Activations