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. 40588
    Prev
    Next
    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting decimal numeric tokens (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
     strategies
    -0.07
     Song
    -0.07
     song
    -0.07
     channel
    -0.06
     celebrated
    -0.06
     Actor
    -0.06
     hugged
    -0.06
     Connecting
    -0.06
     Gospel
    -0.06
     suburb
    -0.06
    POSITIVE LOGITS
     edilen
    0.07
     вполне
    0.07
     geniş
    0.07
    aydı
    0.07
    oct
    0.07
     любов
    0.07
    .blit
    0.07
     продаж
    0.06
    rodní
    0.06
    ัพ
    0.06
    Activations Density 0.016%

    No Known Activations