© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110273
    Prev
    Next
    INDEX
    Explanations

    specimen

    np_max-act · gemini-2.0-flash

    The neuron fires on the factual, taxonomic‐style statements about specimens (counts, dates, collectors, and collection events) in scientific descriptions.

    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
     Robots
    -0.06
     frenzy
    -0.06
     Cheryl
    -0.06
    kf
    -0.06
    alty
    -0.06
    (post
    -0.06
    //----------------
    -0.05
     adlandır
    -0.05
    аков
    -0.05
    发布
    -0.05
    POSITIVE LOGITS
     Wax
    0.07
    Queryable
    0.07
    "';
    0.07
     LA
    0.07
     arbe
    0.07
     proced
    0.06
    .dropdown
    0.06
    Applications
    0.06
     organisations
    0.06
     believed
    0.06
    Activations Density 0.014%

    No Known Activations