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. 110697
    Prev
    Next
    INDEX
    Explanations

    single letters

    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
    creature
    -0.07
     літерату
    -0.07
    _enemy
    -0.07
    presence
    -0.07
    ันก
    -0.07
    peace
    -0.07
    .vol
    -0.07
    rej
    -0.07
     vbox
    -0.06
    ेच
    -0.06
    POSITIVE LOGITS
     procedures
    0.06
     aide
    0.06
    инг
    0.06
     дані
    0.06
    =min
    0.06
     densities
    0.06
     administrators
    0.06
    ("__
    0.06
     नय
    0.06
     チ
    0.06
    Activations Density 0.005%

    No Known Activations