© 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
    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. 52963
    Prev
    Next
    INDEX
    Explanations

    code and math expressions

    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
     eliminated
    -0.06
     POS
    -0.06
     Fus
    -0.06
    urr
    -0.06
     fut
    -0.06
    _variant
    -0.06
     conservatism
    -0.06
    по
    -0.06
     hậu
    -0.06
    /fr
    -0.06
    POSITIVE LOGITS
     znění
    0.07
     Regel
    0.07
     نفت
    0.06
    Shutdown
    0.06
    _disable
    0.06
    mentioned
    0.06
    apse
    0.06
     lãi
    0.06
     routinely
    0.06
     tamil
    0.06
    Activations Density 0.002%

    No Known Activations