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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 47141
    Prev
    Next
    INDEX
    Explanations

    dolor

    np_max-act · gemini-2.0-flash

    HTML and CSS code snippets for web design.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    bstract
    -0.06
     Civilization
    -0.06
    _dt
    -0.06
     Town
    -0.06
    .em
    -0.06
    NEXT
    -0.06
    .Left
    -0.06
    Transient
    -0.06
     Byron
    -0.06
     ACCEPT
    -0.06
    POSITIVE LOGITS
     dolor
    0.10
     solid
    0.07
     قر
    0.07
    987
    0.07
     sl
    0.07
    ero
    0.06
    343
    0.06
    /re
    0.06
     research
    0.06
     painful
    0.06
    Activations Density 0.000%

    No Known Activations