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. 40521
    Prev
    Next
    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash

    The neuron responds strongly to numerals that appear as part of dates or year ranges.

    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
    adelphia
    -0.08
     пла
    -0.07
    (Block
    -0.07
     placeholder
    -0.07
     sub
    -0.06
    映
    -0.06
     JE
    -0.06
    longleftrightarrow
    -0.06
     빌
    -0.06
    _human
    -0.06
    POSITIVE LOGITS
    (ByVal
    0.07
    float
    0.06
    frei
    0.06
     beyond
    0.06
    ัญช
    0.06
     stations
    0.06
     />}↵
    0.06
    .Unicode
    0.05
    fwrite
    0.05
    .l
    0.05
    Activations Density 0.082%

    No Known Activations