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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30403
    Prev
    Next
    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on terms that specify study sample sizes or cohort descriptions—e.g. “all,” numeric counts, and words denoting inclusion of subjects.

    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
     ellipse
    -0.07
    れた
    -0.06
    BigInt
    -0.06
    로운
    -0.06
     consultants
    -0.06
     sufficiently
    -0.06
     quem
    -0.06
     composers
    -0.06
    employed
    -0.06
     зв
    -0.06
    POSITIVE LOGITS
    _tb
    0.06
    บาย
    0.06
     تع
    0.06
     mümkün
    0.06
    meyi
    0.06
     Fibonacci
    0.06
    glob
    0.06
    	glVertex
    0.06
    ائق
    0.06
    /'.
    0.06
    Activations Density 0.011%

    No Known Activations