© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 105347
    Prev
    Next
    INDEX
    Explanations

    Programming / code

    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
     Phú
    -0.06
    ени
    -0.06
     lava
    -0.06
    awner
    -0.06
    .ReadAsStringAsync
    -0.06
    ети
    -0.06
    ISIBLE
    -0.06
    '];?>
    -0.06
     تبلی
    -0.06
    ่าร
    -0.06
    POSITIVE LOGITS
     dvoj
    0.07
     opt
    0.07
    ジョ
    0.07
     모두
    0.06
     найбільш
    0.06
    morph
    0.06
     серпня
    0.06
    ilit
    0.06
     superiority
    0.06
    PEG
    0.06
    Activations Density 0.005%

    No Known Activations