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. 119915
    Prev
    Next
    INDEX
    Explanations

    null

    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
    Ws
    -0.08
    Summary
    -0.07
    Span
    -0.07
    forge
    -0.06
     سن
    -0.06
    眾
    -0.06
    ction
    -0.06
     Urdu
    -0.06
    อ
    -0.06
    tiles
    -0.06
    POSITIVE LOGITS
     Premiere
    0.06
    :'',
    0.06
    .Pass
    0.06
    ())),↵
    0.06
     Heller
    0.06
    (cx
    0.06
    ermo
    0.06
     لد
    0.06
     двад
    0.06
     구매
    0.06
    Activations Density 0.013%

    No Known Activations