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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 37281
    Prev
    Next
    INDEX
    Explanations

    prepositions and "to"

    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
    associate
    -0.08
    aval
    -0.08
    �
    -0.07
    argent
    -0.07
    اجه
    -0.07
     svůj
    -0.07
     undesirable
    -0.06
     получения
    -0.06
     jumps
    -0.06
     coorden
    -0.06
    POSITIVE LOGITS
    chw
    0.06
    _THIS
    0.06
     navig
    0.06
    (forms
    0.06
    $results
    0.06
     Setter
    0.06
    _SHA
    0.06
    .strip
    0.05
    RFC
    0.05
    .setImage
    0.05
    Activations Density 0.056%

    No Known Activations