Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53858
    Prev
    Next
    INDEX
    Explanations

    brackets

    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
     vast
    -0.07
     Arc
    -0.07
     launched
    -0.07
     pellet
    -0.06
     committee
    -0.06
     flagged
    -0.06
     approved
    -0.06
    -export
    -0.06
    Promise
    -0.06
    َّ
    -0.06
    POSITIVE LOGITS
    .ReadAllText
    0.07
     {
    ↵
    ↵
    ↵
    0.07
    ~↵↵
    0.07
     cigaret
    0.06
    víc
    0.06
    (Abstract
    0.06
     �
    0.06
    /is
    0.06
    scopes
    0.06
     dame
    0.06
    Activations Density 0.005%

    No Known Activations