© 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. 125970
    Prev
    Next
    INDEX
    Explanations

    ag

    np_max-act · gemini-2.0-flash

    This neuron is specialized to detect occurrences of the term “nystagmus” (including its subword parts) in the text.

    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
     Hiện
    -0.07
    riends
    -0.06
    esterday
    -0.06
    .friend
    -0.06
    mtree
    -0.06
    	J
    -0.06
     ↵↵↵
    -0.06
    .getOrElse
    -0.06
    Door
    -0.06
    ům
    -0.06
    POSITIVE LOGITS
     stakeholders
    0.07
    _softmax
    0.07
    лон
    0.07
     sembl
    0.06
     fencing
    0.06
     bırak
    0.06
     MessageBox
    0.06
    -guard
    0.06
    -flow
    0.06
    .thumb
    0.06
    Activations Density 0.001%

    No Known Activations