© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7968
    Prev
    Next
    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐style syntax (e.g. code keywords, symbols, and structure) rather than ordinary prose.

    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
    Dirty
    -0.06
    mail
    -0.06
    .Aggressive
    -0.06
     Starr
    -0.06
     constraint
    -0.06
     tumor
    -0.06
     جمعیت
    -0.06
     Batt
    -0.06
    ونه
    -0.06
    src
    -0.06
    POSITIVE LOGITS
    	Long
    0.07
     quantitative
    0.06
    alarında
    0.06
     spills
    0.06
    _lat
    0.06
     extingu
    0.06
    าหล
    0.06
     자연
    0.06
    ulpt
    0.06
     queues
    0.06
    Activations Density 0.013%

    No Known Activations