© 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. 125063
    Prev
    Next
    INDEX
    Explanations

    math symbols and operators

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that mark the structure of formal logical‐query expressions—e.g. IN, JOIN, and the surrounding parentheses.

    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
    Profiles
    -0.06
     staring
    -0.06
    (UUID
    -0.06
    <x
    -0.06
    Appe
    -0.06
    [u
    -0.06
     Messenger
    -0.06
    _Int
    -0.06
    aja
    -0.06
    POSITIVE LOGITS
    ……………………
    0.07
     materials
    0.07
    =$
    0.07
     blasts
    0.06
     dle
    0.06
     a
    0.06
     Frequently
    0.06
     =$
    0.06
    getLast
    0.06
     seven
    0.06
    Activations Density 0.019%

    No Known Activations