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. 110787
    Prev
    Next
    INDEX
    Explanations

    time

    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
     bfs
    -0.06
     ANAL
    -0.06
    folios
    -0.06
    perc
    -0.05
    imating
    -0.05
    igua
    -0.05
    cü
    -0.05
    "urls
    -0.05
     Paras
    -0.05
    &id
    -0.05
    POSITIVE LOGITS
     mean
    0.07
    rieb
    0.07
    .editor
    0.07
     ago
    0.07
     zk
    0.07
     waitFor
    0.06
    _access
    0.06
     Mull
    0.06
     processing
    0.06
     Slater
    0.06
    Activations Density 0.003%

    No Known Activations