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. 109822
    Prev
    Next
    INDEX
    Explanations

    +

    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
     fy
    -0.07
    _than
    -0.07
     grease
    -0.06
    _Framework
    -0.06
     efficacy
    -0.06
     kp
    -0.06
     pool
    -0.06
    Great
    -0.06
    yg
    -0.06
     visibly
    -0.06
    POSITIVE LOGITS
     KC
    0.07
     argc
    0.06
    (using
    0.06
    Logged
    0.06
     instantiate
    0.06
     educate
    0.06
    .indent
    0.06
    erek
    0.06
     inputStream
    0.06
     guesses
    0.06
    Activations Density 0.032%

    No Known Activations