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. 40645
    Prev
    Next
    INDEX
    Explanations

    at

    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
    uede
    -0.06
     larger
    -0.06
     predators
    -0.06
     �
    -0.06
    .keras
    -0.06
     čtyř
    -0.06
    Logging
    -0.06
     subgroup
    -0.06
     муль
    -0.06
    uí
    -0.06
    POSITIVE LOGITS
    _ATTR
    0.07
    )r
    0.06
     Short
    0.06
    Short
    0.06
     Regional
    0.06
    .at
    0.06
     sát
    0.06
     Арх
    0.06
    GRAM
    0.06
    College
    0.06
    Activations Density 0.040%

    No Known Activations