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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128523
    Prev
    Next
    INDEX
    Explanations

    Feedback

    np_max-act · gemini-2.0-flash

    The neuron activates on terminology related to editorial feedback and scholarly discourse (e.g. “comments,” “response,” “reply,” “version,” “reviewer”).

    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
     gode
    -0.06
    ic
    -0.06
    ्क
    -0.06
    ــــ
    -0.06
    _dd
    -0.06
    ("^
    -0.06
     šť
    -0.06
     malt
    -0.05
     ส
    -0.05
    ис
    -0.05
    POSITIVE LOGITS
     hodně
    0.07
    egasus
    0.06
    ểm
    0.06
    rok
    0.06
    екти
    0.06
    avax
    0.06
     معد
    0.06
     Lola
    0.06
     répond
    0.06
    OUND
    0.06
    Activations Density 0.020%

    No Known Activations