© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90865
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the token “to,” i.e. the infinitival marker “to.”

    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
     بأ
    -0.07
     quadrant
    -0.07
     stressful
    -0.06
     öne
    -0.06
    -kind
    -0.06
    ()).
    -0.06
     βα
    -0.06
     plugs
    -0.06
    %.
    -0.06
    不得
    -0.06
    POSITIVE LOGITS
     combos
    0.07
     Coroutine
    0.06
     internacional
    0.06
    ilik
    0.06
     Language
    0.06
    소년
    0.06
    td
    0.06
     TOUCH
    0.06
    ARS
    0.06
    elage
    0.06
    Activations Density 0.028%

    No Known Activations