© 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. 30029
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron fires on topology-related terms, especially words like “continuous,” “closed,” and “compact.”

    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
    _add
    -0.07
     जबक
    -0.07
    антаж
    -0.07
    _default
    -0.07
    .Match
    -0.06
    FlowLayout
    -0.06
     لكن
    -0.06
    _EXTERNAL
    -0.06
     Detector
    -0.06
    .Microsoft
    -0.06
    POSITIVE LOGITS
     referendum
    0.07
    CW
    0.06
    .listener
    0.06
    .formData
    0.06
    -upload
    0.06
    Subscriber
    0.06
     」
    0.06
     fileId
    0.06
    pin
    0.06
     neust
    0.06
    Activations Density 0.028%

    No Known Activations