© 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. 56224
    Prev
    Next
    INDEX
    Explanations

    3

    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
     υπάρχ
    -0.06
    achine
    -0.06
    ウェ
    -0.06
    徐
    -0.06
     sabot
    -0.06
    Israeli
    -0.06
     에
    -0.06
     Верхов
    -0.06
    echn
    -0.06
    扱
    -0.06
    POSITIVE LOGITS
    target
    0.07
    ้ด
    0.06
    []}
    0.06
     IF
    0.06
     FOUND
    0.06
     KH
    0.06
    uiten
    0.06
    ingerprint
    0.06
     tossing
    0.06
    _CENTER
    0.06
    Activations Density 0.001%

    No Known Activations