Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 80605
    Prev
    Next
    INDEX
    Explanations

    a

    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
     setter
    -0.06
     işi
    -0.06
     van
    -0.06
     crafts
    -0.06
    —a
    -0.06
    	align
    -0.06
     victorious
    -0.06
    Speed
    -0.06
     температура
    -0.06
     foreground
    -0.06
    POSITIVE LOGITS
    (fabs
    0.06
    بية
    0.06
     اب
    0.06
    ้น
    0.06
    _dec
    0.06
     н
    0.06
     наб
    0.06
    adf
    0.06
    akens
    0.06
    '||
    0.06
    Activations Density 0.227%

    No Known Activations