© 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. 109808
    Prev
    Next
    INDEX
    Explanations

    prepositions to for

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the infinitival “to” (the marker introducing a “to + verb” construction).

    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
    _changes
    -0.07
     zwei
    -0.06
     een
    -0.06
     tens
    -0.06
     enerji
    -0.06
    -Cds
    -0.06
     productos
    -0.06
     perpetrator
    -0.06
    _records
    -0.06
    .interpolate
    -0.06
    POSITIVE LOGITS
    кти
    0.07
    512
    0.07
    ksam
    0.07
    �蛛
    0.06
    AMPLE
    0.06
    源
    0.06
     Docker
    0.06
     pocházet
    0.06
    LowerCase
    0.06
     acompanh
    0.06
    Activations Density 0.087%

    No Known Activations