© 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. 58216
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “reason(s)” in contexts that introduce motives or justifications (e.g. “reasons to …”).

    oai_token-act-pair · o4-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
    "What
    -0.07
    “What
    -0.07
    響
    -0.07
    win
    -0.06
    งหมด
    -0.06
    Palette
    -0.06
    _door
    -0.06
    901
    -0.06
    Stats
    -0.06
    223
    -0.06
    POSITIVE LOGITS
     क
    0.07
     She
    0.07
     무료
    0.06
     collective
    0.06
    idx
    0.06
     basename
    0.06
    chapter
    0.06
     рассчит
    0.06
     He
    0.06
     случа
    0.06
    Activations Density 0.019%

    No Known Activations