© 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. 90735
    Prev
    Next
    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash

    The neuron fires on the prompt’s field-label keywords—e.g. “Title,” “Description,” “Also,” etc.—marking the instruction sections.

    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
    Boundary
    -0.08
    _entries
    -0.07
    rega
    -0.07
    (entries
    -0.06
     integr
    -0.06
    енно
    -0.06
    ταν
    -0.06
    хо
    -0.06
     kans
    -0.06
    elsing
    -0.06
    POSITIVE LOGITS
    =d
    0.07
     sugars
    0.06
    .GET
    0.06
    ')}}↵
    0.06
    -slot
    0.06
     Natural
    0.06
     natural
    0.06
     출
    0.06
    .getEmail
    0.06
     (+
    0.06
    Activations Density 0.025%

    No Known Activations