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. 80554
    Prev
    Next
    INDEX
    Explanations

    Code/configuration snippets

    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
    _recommend
    -0.07
     Separate
    -0.07
    xA
    -0.07
    spent
    -0.06
     manera
    -0.06
     sce
    -0.06
    еня
    -0.06
     continually
    -0.06
    _emails
    -0.06
    -memory
    -0.06
    POSITIVE LOGITS
    .us
    0.06
    .calculate
    0.06
    лятор
    0.06
    Repo
    0.06
     Neighborhood
    0.06
     aborted
    0.06
    @author
    0.06
     enthusiast
    0.06
     PARTIC
    0.06
    Formation
    0.06
    Activations Density 0.038%

    No Known Activations