© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 60472
    Prev
    Next
    INDEX
    Explanations

    cleaning

    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
    ‌هاي
    -0.07
     метал
    -0.06
    groupName
    -0.06
    Τα
    -0.06
    Φ
    -0.06
     fly
    -0.06
    	extern
    -0.06
    plugin
    -0.06
     Nigel
    -0.06
     placements
    -0.06
    POSITIVE LOGITS
    [state
    0.07
    <|start_header_id|>
    0.07
    .GONE
    0.07
     Yankees
    0.07
     起
    0.06
     BBB
    0.06
    ihu
    0.06
    (width
    0.06
    \uC
    0.06
    .closePath
    0.06
    Activations Density 0.015%

    No Known Activations