© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126146
    Prev
    Next
    INDEX
    Explanations

    anchoring proteins

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of glycosylphosphatidylinositol (GPI) anchors or anchoring.

    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
    教授
    -0.06
     canceled
    -0.06
    gd
    -0.06
     blond
    -0.06
     Rodriguez
    -0.06
    PressEvent
    -0.06
     Роз
    -0.06
    (using
    -0.06
    uses
    -0.06
    _revision
    -0.06
    POSITIVE LOGITS
     tether
    0.08
    _AF
    0.06
    connexion
    0.06
     连
    0.06
     cljs
    0.06
    _ComCallableWrapper
    0.06
     поль
    0.06
     сах
    0.06
     cria
    0.06
    خته
    0.06
    Activations Density 0.002%

    No Known Activations