Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130333
    Prev
    Next
    INDEX
    Explanations

    units of measure

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements and their units (e.g., temperatures in °F/°C or distances in miles).

    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
    23
    -0.06
    vid
    -0.06
     ontology
    -0.06
    /feed
    -0.06
    YSQL
    -0.06
    udd
    -0.06
    escort
    -0.06
    .physics
    -0.06
     Fantastic
    -0.06
    _DEC
    -0.06
    POSITIVE LOGITS
     quand
    0.07
     国
    0.06
     Mesa
    0.06
     clave
    0.06
    :Any
    0.06
    .Here
    0.06
     synagogue
    0.06
     централь
    0.05
     grues
    0.05
    utsch
    0.05
    Activations Density 0.037%

    No Known Activations