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. 86080
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on the first substantive word of a new text block or sentence segment, marking the start of paragraphs or major sections.

    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
    ždy
    -0.08
     recreation
    -0.06
     ful
    -0.06
     rejo
    -0.06
     definitely
    -0.06
     provisional
    -0.06
     rar
    -0.06
    adalafil
    -0.06
    292
    -0.06
     Feast
    -0.06
    POSITIVE LOGITS
    >/<
    0.07
    .community
    0.07
    ویه
    0.07
     Grammy
    0.07
    	day
    0.06
     takson
    0.06
     prolong
    0.06
    ляти
    0.06
     pues
    0.06
     Stripe
    0.06
    Activations Density 0.009%

    No Known Activations