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. 23-RESID-POST-AA
    6. 40733
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เคล
    -0.07
    cott
    -0.07
    난
    -0.07
     Rox
    -0.06
     अन
    -0.06
     risky
    -0.06
     rf
    -0.06
     citrus
    -0.06
    sendKeys
    -0.06
     windshield
    -0.06
    POSITIVE LOGITS
    _recursive
    0.07
    indices
    0.06
    _nums
    0.06
    .READ
    0.06
     Vincent
    0.06
    acia
    0.06
    ootball
    0.06
     kimse
    0.06
     Knight
    0.06
     Tarihi
    0.06
    Activations Density 0.132%

    No Known Activations