© 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
    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. 91935
    Prev
    Next
    INDEX
    Explanations

    detox/cleansing

    np_max-act · gemini-2.0-flash

    The neuron activates strongly on words referring to bodily “detox” or “cleanse” routines—i.e. mentions of detoxification, cleansing, or colon‐cleansing.

    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
     Dialogue
    -0.07
    ्वय
    -0.06
    ünüz
    -0.06
    hta
    -0.06
    fst
    -0.06
     mix
    -0.06
    _Project
    -0.06
    нувся
    -0.06
    ัฒนา
    -0.06
    Pack
    -0.06
    POSITIVE LOGITS
    .simps
    0.07
     Rt
    0.07
    .cancel
    0.06
     chr
    0.06
     heatmap
    0.06
     outbreak
    0.06
    estion
    0.06
     Inf
    0.06
     (![
    0.06
    ='".
    0.06
    Activations Density 0.004%

    No Known Activations