© 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. 11-RESID-POST-AA
    11. 109649
    Prev
    Next
    INDEX
    Explanations

    not working, questions

    np_max-act · gemini-2.0-flash

    The neuron fires on phrasing in the question title or description that flags a failure or broken behavior (e.g. “not working,” “expected,” “error”).

    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
     Slam
    -0.07
     дити
    -0.06
    .dateFormat
    -0.06
    �
    -0.06
    .optimize
    -0.06
    .invoice
    -0.06
     xuống
    -0.06
    (TAG
    -0.06
    (report
    -0.06
    .getUserId
    -0.06
    POSITIVE LOGITS
    ा-
    0.07
    ||
    0.06
    hel
    0.06
    Use
    0.06
    nya
    0.06
    collision
    0.06
    RESH
    0.06
     Floyd
    0.06
    *D
    0.06
     seamlessly
    0.06
    Activations Density 0.022%

    No Known Activations