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. 86327
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron detects descriptive phrases explaining how a chart or graph encodes and represents data (e.g. “rectangular bars to represent the frequency or quantity of data”).

    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
    Pes
    -0.07
     jednoduch
    -0.07
    (pp
    -0.07
     Fro
    -0.06
     Valerie
    -0.06
     وارد
    -0.06
     ̄ ̄
    -0.06
    งก
    -0.06
     Fak
    -0.06
    nict
    -0.06
    POSITIVE LOGITS
    <string
    0.06
     leaving
    0.06
     Bahrain
    0.06
     Tel
    0.06
     exagger
    0.05
    ΙΑ
    0.05
     pict
    0.05
     enrich
    0.05
     Kerala
    0.05
    ="./
    0.05
    Activations Density 0.015%

    No Known Activations