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. 130636
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens that represent floating‐point values (tokens containing digits with decimal fractions).

    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
    converter
    -0.07
    يين
    -0.07
    _cmp
    -0.07
     BigNumber
    -0.07
    有一
    -0.07
    二
    -0.06
    ieri
    -0.06
    herent
    -0.06
    한테
    -0.06
    -Free
    -0.06
    POSITIVE LOGITS
    enedor
    0.07
     garn
    0.07
     errorMsg
    0.06
     düzenlem
    0.06
     tasarım
    0.06
    sPid
    0.06
     MySqlConnection
    0.06
    //:
    0.06
     Hack
    0.06
     tato
    0.06
    Activations Density 0.009%

    No Known Activations