© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 100164
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     teşkil
    -0.07
    �
    -0.07
    JsonValue
    -0.06
     Amerikan
    -0.06
     Opinion
    -0.06
    >y
    -0.06
     Bry
    -0.06
    ujícím
    -0.06
     позвол
    -0.06
    .typ
    -0.06
    POSITIVE LOGITS
    abilité
    0.07
    .Light
    0.06
    .embedding
    0.06
    だった
    0.06
    であった
    0.06
     enactment
    0.06
     antes
    0.06
     celebrates
    0.06
    .build
    0.06
     จำ
    0.06
    Activations Density 0.025%

    No Known Activations