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. 11-RESID-POST-AA
    6. 80766
    Prev
    Next
    INDEX
    Explanations

    intense

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .nio
    -0.06
     brightest
    -0.06
     Vanilla
    -0.06
     Dickens
    -0.06
     
    -0.06
    'int
    -0.06
         ↵
    -0.06
    endant
    -0.06
    NaN
    -0.06
    hp
    -0.06
    POSITIVE LOGITS
    фі
    0.07
    _WEEK
    0.06
     deltas
    0.06
    _Set
    0.06
    von
    0.06
    UCCESS
    0.06
     whose
    0.06
    ='-
    0.06
    とな
    0.06
     Limited
    0.06
    Activations Density 0.154%

    No Known Activations