© 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. 110277
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash

    discussions about the design and function of dish racks in the context of food service industries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects subjective or hedging language—words and short phrases that signal opinion, uncertainty, or stance (e.g. arguably, perhaps, I think).

    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
     있는데
    -0.07
    gré
    -0.06
     엔
    -0.06
    .XPath
    -0.06
    _MD
    -0.06
    "]');↵
    -0.06
    िसस
    -0.06
     gifts
    -0.06
    Weights
    -0.06
    458
    -0.06
    POSITIVE LOGITS
     schizophren
    0.07
     elektronik
    0.07
     baise
    0.06
    =batch
    0.06
    _putchar
    0.06
     Doğu
    0.06
     Bio
    0.06
    Endian
    0.06
    [g
    0.06
    젝
    0.06
    Activations Density 0.065%

    No Known Activations