Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 52047
    Prev
    Next
    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash

    details about specific medical conditions and their characteristics.

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

    The neuron lights up on modal/auxiliary words expressing possibility or capability (e.g. “can,” “may,” “occur,” “also”) in clinical/descriptive statements.

    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
                    
    ↵
    -0.07
    FX
    -0.06
     proceed
    -0.06
    sched
    -0.06
     splash
    -0.06
    asca
    -0.06
     acid
    -0.06
    lers
    -0.06
    34
    -0.06
    守
    -0.06
    POSITIVE LOGITS
     Hội
    0.07
     Francie
    0.07
     бла
    0.07
     childcare
    0.06
     shitty
    0.06
    -Re
    0.06
     Assy
    0.06
     benöt
    0.06
     칼
    0.06
    .isOpen
    0.06
    Activations Density 0.081%

    No Known Activations