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. 40545
    Prev
    Next
    INDEX
    Explanations

    Error

    np_max-act · gemini-2.0-flash

    The neuron detects Python exception tracebacks, especially the “AttributeError” error lines.

    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
     پیشنه
    -0.08
     collapse
    -0.07
     comedy
    -0.07
    穴
    -0.07
     हज
    -0.06
    	as
    -0.06
     eldest
    -0.06
     lx
    -0.06
     getParent
    -0.06
     Centre
    -0.06
    POSITIVE LOGITS
    ове
    0.07
    =target
    0.06
     PropertyInfo
    0.06
    sville
    0.06
    tolist
    0.06
     одні
    0.06
    ива
    0.06
     yarat
    0.06
    phins
    0.06
    リカ
    0.06
    Activations Density 0.006%

    No Known Activations