© 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. 9355
    Prev
    Next
    INDEX
    Explanations

    terms

    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
     сіль
    -0.07
    graf
    -0.07
     mostr
    -0.07
     Liga
    -0.07
     CIF
    -0.07
    .Linear
    -0.06
     نامه
    -0.06
    _partner
    -0.06
    �n
    -0.06
    porno
    -0.06
    POSITIVE LOGITS
    lanır
    0.06
     statement
    0.06
    George
    0.06
    接着
    0.06
    Republicans
    0.06
     treat
    0.06
     انتخاب
    0.06
    <|begin_of_text|>
    0.06
     conditional
    0.06
     يع
    0.06
    Activations Density 0.001%

    No Known Activations