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. 123287
    Prev
    Next
    INDEX
    Explanations

    code

    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
     CAST
    -0.07
    xef
    -0.07
    xCF
    -0.06
    seven
    -0.06
     тут
    -0.06
     Св
    -0.06
     рук
    -0.06
     Bunu
    -0.06
     Amerik
    -0.06
    >`;↵
    -0.06
    POSITIVE LOGITS
     undocumented
    0.06
     odd
    0.06
    -api
    0.06
     BOTTOM
    0.06
     pale
    0.06
     Odd
    0.06
     celebration
    0.06
    anks
    0.06
     string
    0.06
     tops
    0.06
    Activations Density 0.000%

    No Known Activations