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. 130534
    Prev
    Next
    INDEX
    Explanations

    sides

    np_max-act · gemini-2.0-flash

    words related to demographic statistics and societal trends.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron primarily responds to mentions of opposing “sides” (e.g. “both sides”) in conflict or comparison contexts.

    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
     malaria
    -0.07
     Sega
    -0.07
     volunte
    -0.07
     Refugee
    -0.06
     blasting
    -0.06
     demande
    -0.06
    ctrl
    -0.06
     Victor
    -0.06
    CHR
    -0.06
    _life
    -0.06
    POSITIVE LOGITS
    对方
    0.07
    ש
    0.06
    Neutral
    0.06
     sides
    0.06
    -push
    0.06
     �
    0.06
     cosplay
    0.06
    .toObject
    0.06
    _Success
    0.06
    Broken
    0.06
    Activations Density 0.009%

    No Known Activations