© 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. 54030
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by 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
    +C
    -0.07
    ผล
    -0.07
     Wh
    -0.07
    NavBar
    -0.07
    Ford
    -0.06
     [[[
    -0.06
    D
    -0.06
    ê
    -0.06
    _AV
    -0.06
    rbrakk
    -0.06
    POSITIVE LOGITS
     tumble
    0.07
    donnees
    0.07
    )));
    ↵
    0.07
    rax
    0.07
    ErrorResponse
    0.06
     citas
    0.06
     encountering
    0.06
    _reading
    0.06
    τού
    0.06
    @update
    0.06
    Activations Density 0.100%

    No Known Activations