© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56945
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of procedural claim language—particularly the word “method” (as in “method for …”) in patent‐style text.

    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
    教
    -0.07
     TIM
    -0.06
     seh
    -0.06
    Hen
    -0.06
    于是
    -0.06
     animal
    -0.06
     odense
    -0.06
    _PERSON
    -0.06
    哭
    -0.06
    	n
    -0.06
    POSITIVE LOGITS
     parch
    0.07
    кість
    0.07
     graduates
    0.07
     Origin
    0.06
    _WEEK
    0.06
    Bulk
    0.06
    CompanyName
    0.06
     nuisance
    0.06
     slowed
    0.06
     Ala
    0.06
    Activations Density 0.009%

    No Known Activations