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. 123397
    Prev
    Next
    INDEX
    Explanations

    school data in parentheses

    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
     रखन
    -0.07
    _attempt
    -0.07
    -Jan
    -0.07
    복
    -0.06
    .validator
    -0.06
    _DELAY
    -0.06
    .Never
    -0.06
     diğer
    -0.06
    ρέπει
    -0.06
    耳
    -0.06
    POSITIVE LOGITS
    344
    0.07
     çı
    0.07
     Swedish
    0.06
     German
    0.06
    θυν
    0.06
     Hungarian
    0.06
     definitive
    0.06
     \<^
    0.06
     cond
    0.06
     ubic
    0.06
    Activations Density 0.007%

    No Known Activations