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. 86225
    Prev
    Next
    INDEX
    Explanations

    Website/SEO content

    np_max-act · gemini-2.0-flash

    The neuron is specialized for spotting title-style or headline phrases composed of multiple consecutive capitalized words (e.g. “Best Real Estate Agent In Walnut Creek CA,” “Free Fast Food Places,” etc.).

    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
     Spice
    -0.07
     mcc
    -0.07
    .ac
    -0.06
     nového
    -0.06
     borderWidth
    -0.06
    many
    -0.06
     Apprentice
    -0.06
    ADIUS
    -0.06
     smashed
    -0.06
    _axes
    -0.06
    POSITIVE LOGITS
    (start
    0.07
     Emer
    0.07
    App
    0.06
    -next
    0.06
    allowed
    0.06
     Undert
    0.06
    -we
    0.06
    tatus
    0.06
    iders
    0.06
    Diff
    0.06
    Activations Density 0.056%

    No Known Activations