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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 124434
    Prev
    Next
    INDEX
    Explanations

    athletes

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пти
    -0.06
     ngu
    -0.06
     mi
    -0.06
    _val
    -0.06
    arp
    -0.06
     transcription
    -0.06
    溶
    -0.06
     Ng
    -0.06
    ?>↵
    -0.06
    อส
    -0.06
    POSITIVE LOGITS
     spielen
    0.08
    MeasureSpec
    0.07
     fits
    0.07
     dissent
    0.07
    WAYS
    0.07
     hoped
    0.07
     RELATED
    0.07
    <|begin_of_text|>
    0.06
    阅读
    0.06
     scrim
    0.06
    Activations Density 0.046%

    No Known Activations