© 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. 41518
    Prev
    Next
    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that appear in factual declarative statements (e.g. “This is a basic mathematical fact…”).

    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
    되어
    -0.07
     Pediatrics
    -0.06
    _squared
    -0.06
     Trotsky
    -0.06
    SGlobal
    -0.06
     Appropri
    -0.06
     spel
    -0.06
    .shopping
    -0.06
    -theme
    -0.06
    EntryPoint
    -0.06
    POSITIVE LOGITS
    urm
    0.06
     Designed
    0.06
    Still
    0.06
    Double
    0.06
    Section
    0.06
     resonate
    0.06
    product
    0.06
     quarter
    0.06
    .Many
    0.06
    _quick
    0.06
    Activations Density 0.052%

    No Known Activations