© 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. 770
    Prev
    Next
    INDEX
    Explanations

    IN

    np_max-act · gemini-2.0-flash

    The neuron responds to comparatively rare or unusual tokens—acronyms, jargon, uncommon words, and other low‐frequency terms.

    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
    uxtap
    -0.07
     kur
    -0.07
    ورش
    -0.07
    Opp
    -0.07
    awks
    -0.06
    Slides
    -0.06
    ارد
    -0.06
     biking
    -0.06
    @PostMapping
    -0.06
     ⌒
    -0.06
    POSITIVE LOGITS
     _↵↵
    0.06
     residue
    0.06
    .start
    0.06
    -logo
    0.06
     zboží
    0.06
     cheating
    0.06
     выход
    0.06
     todas
    0.06
    _DIFF
    0.06
     Vaccine
    0.06
    Activations Density 0.024%

    No Known Activations