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. 130213
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    scientific terminology related to herbal compounds and their effects.

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

    This neuron fires on phrases that attribute statements or claims to an author or source (e.g. “as X explains,” “according to Y”).

    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
    Mappings
    -0.07
     left
    -0.06
     broken
    -0.06
    _trap
    -0.06
     зроб
    -0.06
    .Db
    -0.06
     appellate
    -0.06
     locked
    -0.06
    TOOLS
    -0.06
     intrigued
    -0.06
    POSITIVE LOGITS
    �
    0.06
     mnemonic
    0.06
    후
    0.06
     ioutil
    0.06
     Carl
    0.06
     inputValue
    0.06
     "-//
    0.06
    ürlich
    0.06
     softer
    0.06
    σεων
    0.06
    Activations Density 0.028%

    No Known Activations