© 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. 109635
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects email/message header fields (e.g. “From:”, “Date:”, “Subject:”) at the start of a message.

    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
     JT
    -0.07
    _quit
    -0.07
    بیر
    -0.06
     Transformers
    -0.06
     قن
    -0.06
    _predicted
    -0.06
     méně
    -0.06
    azard
    -0.06
    egas
    -0.06
     skiing
    -0.06
    POSITIVE LOGITS
    Donate
    0.07
     Honest
    0.06
     činnost
    0.06
    (&
    0.06
    _.
    0.06
     WITHOUT
    0.06
     '\
    0.06
     тысяч
    0.06
     Callback
    0.06
    .codigo
    0.06
    Activations Density 0.002%

    No Known Activations