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. 104681
    Prev
    Next
    INDEX
    Explanations

    practical

    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
    ян
    -0.07
    specified
    -0.07
    dam
    -0.06
    Separator
    -0.06
    ία
    -0.06
    san
    -0.06
    setImage
    -0.06
    eneg
    -0.06
     Modern
    -0.06
     زنان
    -0.06
    POSITIVE LOGITS
     suma
    0.07
     wł
    0.07
     déf
    0.06
    _stop
    0.06
    resolve
    0.06
    Kr
    0.06
    woord
    0.06
    (Cl
    0.06
     markdown
    0.06
    .vstack
    0.06
    Activations Density 0.003%

    No Known Activations