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. 10370
    Prev
    Next
    INDEX
    Explanations

    html/code

    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
     ortak
    -0.08
     Grants
    -0.07
    _TURN
    -0.07
     ASS
    -0.07
    ({↵
    -0.07
     sys
    -0.07
     RCS
    -0.07
     {\
    -0.06
    _bal
    -0.06
    250
    -0.06
    POSITIVE LOGITS
    .isUser
    0.09
     Libre
    0.08
     가져
    0.08
    ρού
    0.07
    stadt
    0.07
    .onStart
    0.07
    атор
    0.07
    rio
    0.07
    ulo
    0.07
    ποι
    0.07
    Activations Density 0.008%

    No Known Activations