© 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. 126693
    Prev
    Next
    INDEX
    Explanations

    flow

    np_max-act · gemini-2.0-flash

    This neuron detects technical references to heat‐kernel or related semigroup operators (e.g. “heat kernel,” “semigroup,” fractional powers of operators).

    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
    Intro
    -0.07
     الف
    -0.07
    infile
    -0.06
    Couldn
    -0.06
     beetle
    -0.06
     Canyon
    -0.06
     vf
    -0.06
     пред
    -0.06
     сама
    -0.06
     kromě
    -0.06
    POSITIVE LOGITS
     vin
    0.07
    líd
    0.07
    LAG
    0.06
    Dates
    0.06
    .After
    0.06
     Alv
    0.06
    มาย
    0.06
     silver
    0.06
     locksmith
    0.06
    _ZERO
    0.06
    Activations Density 0.004%

    No Known Activations