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. 40422
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron is activated by floating‐point numeric literals in code.

    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
    elor
    -0.06
     Grain
    -0.06
     Trot
    -0.06
     bites
    -0.06
     SKF
    -0.06
    Sil
    -0.06
    Assembly
    -0.06
    GRAY
    -0.06
    LOCITY
    -0.06
    ucción
    -0.06
    POSITIVE LOGITS
     loaded
    0.07
    uto
    0.07
    lastname
    0.06
     AUTO
    0.06
    OptionsMenu
    0.06
     ';↵
    0.06
    .failed
    0.06
    .vocab
    0.06
    min
    0.06
    (min
    0.06
    Activations Density 0.004%

    No Known Activations