© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43323
    Prev
    Next
    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    This neuron activates on the substring “for” (e.g. in `for` loops or “filter” calls).

    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
     regulatory
    -0.07
    lox
    -0.06
    ō
    -0.06
     slips
    -0.06
     farewell
    -0.06
     doc
    -0.06
    .multipart
    -0.06
     Cos
    -0.06
     Bu
    -0.06
    BackPressed
    -0.06
    POSITIVE LOGITS
    qp
    0.07
    哪里
    0.07
     섬
    0.07
    	b
    0.06
     účin
    0.06
     хра
    0.06
     estaba
    0.06
     प
    0.06
    圣
    0.06
    ılım
    0.06
    Activations Density 0.099%

    No Known Activations