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. 41369
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     Cater
    -0.07
    .Rule
    -0.06
     Cap
    -0.06
    勝
    -0.06
    Cap
    -0.06
    روش
    -0.06
     majors
    -0.06
     sæ
    -0.06
    SUP
    -0.06
    alph
    -0.06
    POSITIVE LOGITS
    >(
    0.08
    exercise
    0.07
    ROTO
    0.07
    >Please
    0.06
    Had
    0.06
    gger
    0.06
     filament
    0.06
    .Generate
    0.06
     Een
    0.06
     Victims
    0.06
    Activations Density 0.010%

    No Known Activations