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. 130395
    Prev
    Next
    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash

    This neuron fires on rare, long, formal-sounding multisyllabic words.

    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
     nikdy
    -0.06
     emergence
    -0.06
     pride
    -0.06
     backgrounds
    -0.06
     utility
    -0.06
     мод
    -0.06
    مت
    -0.06
     Bug
    -0.06
     humanity
    -0.06
     country
    -0.06
    POSITIVE LOGITS
     between
    0.08
    :init
    0.08
    -before
    0.07
    ­ing
    0.07
    ρο
    0.06
     xor
    0.06
     consisting
    0.06
     BETWEEN
    0.06
    .sav
    0.06
     giữa
    0.06
    Activations Density 0.016%

    No Known Activations