© 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. 15-RESID-POST-AA
    11. 128175
    Prev
    Next
    INDEX
    Explanations

    Personal reflections/blog

    np_max-act · gemini-2.0-flash

    spots long, multi-sentence explanatory assistant responses or model-answer style passages.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للد
    -0.07
    隊
    -0.07
    قی
    -0.07
     فت
    -0.07
     cockpit
    -0.06
     древ
    -0.06
    cala
    -0.06
    ضة
    -0.06
    ihar
    -0.06
    610
    -0.06
    POSITIVE LOGITS
    .Matcher
    0.07
     });↵↵↵↵
    0.07
    wg
    0.07
     ([]
    0.06
    _transition
    0.06
     &&
↵
    0.06
     jede
    0.06
    Jason
    0.06
     zh
    0.06
     \<^
    0.06
    Activations Density 0.015%

    No Known Activations