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. 86154
    Prev
    Next
    INDEX
    Explanations

    scout

    np_max-act · gemini-2.0-flash

    The neuron never activates—it doesn’t detect any particular token or pattern.

    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
     ấm
    -0.07
    AML
    -0.07
    加
    -0.07
    Poly
    -0.06
    Verdana
    -0.06
    aporation
    -0.06
     běž
    -0.06
    PERATURE
    -0.06
     starvation
    -0.06
     giờ
    -0.06
    POSITIVE LOGITS
     scouting
    0.11
     Scout
    0.11
     scout
    0.10
     Recon
    0.08
     Out
    0.08
     scouts
    0.08
     Lab
    0.08
     recon
    0.08
     ascertain
    0.08
     Scouts
    0.07
    Activations Density 0.003%

    No Known Activations