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

    Neuronpedia

    APICircuit 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. 111261
    Prev
    Next
    INDEX
    Explanations

    subscriptions and access

    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
     gray
    -0.07
     grey
    -0.06
     emulate
    -0.06
     Somalia
    -0.06
    [cur
    -0.06
     shaded
    -0.06
     канди
    -0.06
    انس
    -0.06
     rolled
    -0.06
     mc
    -0.06
    POSITIVE LOGITS
    documentation
    0.07
     ).↵↵
    0.07
    VertexUvs
    0.06
     RECE
    0.06
    요
    0.06
    /alert
    0.06
    FAIL
    0.06
    Take
    0.06
     ')';↵
    0.06
     scorn
    0.06
    Activations Density 0.005%

    No Known Activations