© 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. 88933
    Prev
    Next
    INDEX
    Explanations

    simple

    np_max-act · gemini-2.0-flash

    This neuron never activates on any input—it doesn’t detect or respond to any pattern.

    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
    AP
    -0.07
     활용
    -0.06
     Sonic
    -0.06
     CU
    -0.06
     Collect
    -0.06
     Brah
    -0.06
    商
    -0.06
    ``
    -0.06
     (...
    -0.06
     Cox
    -0.06
    POSITIVE LOGITS
     congratulate
    0.07
     küt
    0.06
     rag
    0.06
     barrage
    0.06
    rale
    0.06
    저
    0.06
    .definition
    0.06
    (eval
    0.06
    라이
    0.06
     jede
    0.06
    Activations Density 0.020%

    No Known Activations