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. 86190
    Prev
    Next
    INDEX
    Explanations

    EU

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric tokens (decimal 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
     أعلام
    -0.06
    지도
    -0.06
    inizin
    -0.06
     напри
    -0.06
    .deploy
    -0.06
     پژ
    -0.06
    렉
    -0.06
    _INCLUDED
    -0.06
    _days
    -0.06
    Airport
    -0.06
    POSITIVE LOGITS
    equiv
    0.07
    (dm
    0.06
     wordpress
    0.06
    .DataContext
    0.06
     unnatural
    0.06
     Uruguay
    0.06
    underscore
    0.06
    不同
    0.06
     council
    0.06
     brought
    0.06
    Activations Density 0.000%

    No Known Activations