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. 40645
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on numeric tokens that include decimal points (i.e. floating‐point numbers).

    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
     여
    -0.07
    ograf
    -0.07
    iali
    -0.07
    iano
    -0.07
    EventHandler
    -0.07
    holes
    -0.07
     дія
    -0.07
    _THREAD
    -0.06
    ANNER
    -0.06
    Offer
    -0.06
    POSITIVE LOGITS
     but
    0.22
     But
    0.18
    but
    0.16
    But
    0.15
    _but
    0.13
    ,but
    0.12
    -but
    0.12
    —but
    0.12
    .But
    0.12
     BUT
    0.12
    Activations Density 0.175%

    No Known Activations