© 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. 92611
    Prev
    Next
    INDEX
    Explanations

    electronics/technology

    np_max-act · gemini-2.0-flash

    The neuron activates on technical nouns naming devices, instruments, or methods (e.g. “detector,” “assay,” “codec,” “drive,” etc.).

    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
    พยาบาล
    -0.07
    Specify
    -0.07
    ロー
    -0.07
    \
↵
    -0.06
     incompetent
    -0.06
    рати
    -0.06
     EI
    -0.06
     Rentals
    -0.06
     options
    -0.06
    _void
    -0.06
    POSITIVE LOGITS
     tweak
    0.07
    QRSTUV
    0.07
    ROAD
    0.07
     appointed
    0.07
    ewitness
    0.06
    -rest
    0.06
     ομάδα
    0.06
     streamed
    0.06
     brew
    0.06
    '/>↵
    0.06
    Activations Density 0.065%

    No Known Activations