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. 12319
    Prev
    Next
    INDEX
    Explanations

    orientation

    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
    �
    -0.07
     киш
    -0.06
    <Expression
    -0.06
     uten
    -0.06
    getClass
    -0.06
     irony
    -0.06
     teenage
    -0.06
    isers
    -0.06
     nø
    -0.06
    /process
    -0.06
    POSITIVE LOGITS
    >.↵↵
    0.07
    erek
    0.06
    IDA
    0.06
     Rather
    0.06
    ↵
    0.06
    cluding
    0.06
    102
    0.06
    Copying
    0.06
     So
    0.06
     Important
    0.06
    Activations Density 0.000%

    No Known Activations