© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron is principally responding to the infinitival “to” (and closely related connective or instructional particles).

    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
    Correo
    -0.07
    Pk
    -0.07
     ElementType
    -0.07
     �
    -0.07
     cookbook
    -0.06
    ‌باشد
    -0.06
     نيز
    -0.06
    �
    -0.06
     ук
    -0.06
    的手
    -0.06
    POSITIVE LOGITS
    .setDescription
    0.07
     Vak
    0.07
    STRU
    0.06
     ion
    0.06
    udden
    0.06
    imensional
    0.06
    .Total
    0.06
     Oy
    0.06
     soundtrack
    0.06
    _cell
    0.06
    Activations Density 0.239%

    No Known Activations