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. 130387
    Prev
    Next
    INDEX
    Explanations

    cost, price

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it does not detect any 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
    OMUX
    -0.07
     GP
    -0.07
     handles
    -0.07
     sama
    -0.06
     PD
    -0.06
     headlights
    -0.06
     bullying
    -0.06
     rects
    -0.06
    (tx
    -0.06
     clazz
    -0.06
    POSITIVE LOGITS
     morb
    0.09
     cost
    0.08
     Cost
    0.07
     bilateral
    0.07
    (cost
    0.07
     Subscription
    0.07
     costs
    0.06
     price
    0.06
    座
    0.06
     _|
    0.06
    Activations Density 0.021%

    No Known Activations