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. 27-RESID-POST-AA
    6. 102194
    Prev
    Next
    INDEX
    Explanations

    inclusion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .boot
    -0.07
    Altern
    -0.06
    grily
    -0.06
     seedu
    -0.06
     convinced
    -0.06
    opencv
    -0.06
    Experts
    -0.06
     día
    -0.06
     contrast
    -0.06
    /legal
    -0.06
    POSITIVE LOGITS
     Recording
    0.06
    -shadow
    0.06
    ρι
    0.06
     Resolve
    0.06
    -bot
    0.06
     ukon
    0.06
     Jaguar
    0.05
     With
    0.05
    NSString
    0.05
     laughing
    0.05
    Activations Density 0.464%

    No Known Activations