© 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. 13560
    Prev
    Next
    INDEX
    Explanations

    -f

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of sequential storage elements—specifically “latch” or “flip-flop” circuits.

    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
     mir
    -0.07
     cope
    -0.07
     technician
    -0.06
    Mayor
    -0.06
     м
    -0.06
     unit
    -0.06
    .brand
    -0.06
     kapsamında
    -0.06
     Butterfly
    -0.06
     callers
    -0.06
    POSITIVE LOGITS
    _valor
    0.07
    ['<{
    0.06
    roller
    0.06
     ************************************************
    0.06
    фи
    0.06
    clusive
    0.06
     〉
    0.06
    [:]↵
    0.06
    "].(
    0.06
    .charAt
    0.06
    Activations Density 0.006%

    No Known Activations