© 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. 109418
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron activates on fragments of programming or markup syntax (e.g. inline code, CSS rules, config key bindings), i.e. code-style tokens embedded 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
     redistributed
    -0.07
    ndef
    -0.07
    andom
    -0.07
    747
    -0.06
    ILER
    -0.06
    .serv
    -0.06
     Contribution
    -0.06
    etched
    -0.06
    WA
    -0.06
    ania
    -0.06
    POSITIVE LOGITS
     rpm
    0.07
     Seeing
    0.06
     stirred
    0.06
     Ethiopian
    0.06
    ическая
    0.06
     score
    0.06
     ding
    0.06
    _puts
    0.06
     scores
    0.06
     хроничес
    0.06
    Activations Density 0.000%

    No Known Activations