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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 53540
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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
    _CERT
    -0.07
     evapor
    -0.06
    �
    -0.06
    ther
    -0.06
    _arr
    -0.06
     상태
    -0.06
     RMS
    -0.06
     TP
    -0.06
    blk
    -0.06
    Dlg
    -0.05
    POSITIVE LOGITS
     compt
    0.07
     administrations
    0.07
     �
    0.07
    -END
    0.07
     frowned
    0.07
     началь
    0.07
     nations
    0.07
    —you
    0.07
     churn
    0.07
    (conf
    0.07
    Activations Density 0.016%

    No Known Activations