© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 129972
    Prev
    Next
    INDEX
    Explanations

    ')

    np_max-act · gemini-2.0-flash

    jQuery code — especially jQuery selectors and method calls (e.g., $(...), .on(), .click(), .validate(), .dialog(), .hide(), .submit()).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _arch
    -0.08
    nul
    -0.07
    udad
    -0.07
     Tuy
    -0.06
     Interesting
    -0.06
     Perhaps
    -0.06
    perhaps
    -0.06
    .Enc
    -0.06
    Pr
    -0.06
    Do
    -0.06
    POSITIVE LOGITS
    .Selected
    0.07
     Hern
    0.07
     бра
    0.07
     responsibly
    0.06
     -
    0.06
    `;↵↵
    0.06
     Р
    0.06
     Beatles
    0.06
    оли
    0.06
    :
    0.06
    Activations Density 0.008%

    No Known Activations