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. 11-RESID-POST-AA
    6. 93955
    Prev
    Next
    INDEX
    Explanations

    sparse arrays and vectors

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikler
    -0.06
    ेग
    -0.06
    차
    -0.06
     workshops
    -0.06
     标
    -0.06
     Rams
    -0.06
    800
    -0.06
    _widgets
    -0.06
     magnet
    -0.06
    내
    -0.06
    POSITIVE LOGITS
    :CGRect
    0.07
     ICU
    0.06
     bitte
    0.06
     knull
    0.06
     확실
    0.06
    ,assign
    0.06
    /legal
    0.06
     sahiptir
    0.06
    ;:;:
    0.06
    .FILE
    0.06
    Activations Density 0.070%

    No Known Activations