© 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. 126677
    Prev
    Next
    INDEX
    Explanations

    system information

    np_max-act · gemini-2.0-flash

    The neuron detects references to macOS/Darwin system identifiers (e.g. “Darwin,” “Power Mac,” “Macintosh”).

    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
     Still
    -0.07
    Kitchen
    -0.07
    ิลล
    -0.06
    unk
    -0.06
    _resolver
    -0.06
     프리
    -0.06
     DET
    -0.06
     Assertions
    -0.06
     Natural
    -0.06
     Five
    -0.06
    POSITIVE LOGITS
     răng
    0.06
    одав
    0.06
     مص
    0.06
    "};↵↵
    0.06
     getPosition
    0.06
     تخ
    0.06
    ",(
    0.06
    /embed
    0.06
    	gl
    0.06
    。↵↵
    0.06
    Activations Density 0.016%

    No Known Activations