© 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. 126129
    Prev
    Next
    INDEX
    Explanations

    Berberine, chemical and medical contexts

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on tokens from the names of specific chemical compounds (especially alkaloid-style names ending in “-ine,” e.g. berberine, biotin, yohimbine).

    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
    �
    -0.07
     transistor
    -0.07
    wię
    -0.06
    CI
    -0.06
    mps
    -0.06
    One
    -0.06
     Wong
    -0.06
    �
    -0.06
     дос
    -0.06
    both
    -0.06
    POSITIVE LOGITS
    İTESİ
    0.07
     ORIGINAL
    0.07
     disponible
    0.06
     размещ
    0.06
     случаев
    0.06
    Descriptor
    0.06
    ::_('
    0.06
    Codec
    0.06
     организа
    0.06
     結
    0.06
    Activations Density 0.073%

    No Known Activations