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

    Neuronpedia

    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. 41405
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash

    variables related to sentiment analysis.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags words in the “X should be Y” style instructional phrasing—e.g. “answer,” “should,” “be.”

    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
     justices
    -0.07
    ��
    -0.07
    альной
    -0.06
     스트
    -0.06
     stimulated
    -0.06
    MD
    -0.06
    Spo
    -0.06
    InParameter
    -0.06
     kicker
    -0.06
     trio
    -0.06
    POSITIVE LOGITS
     $("#"
    0.07
     sık
    0.07
     ґ
    0.06
    wav
    0.06
     ([]
    0.06
     MIME
    0.06
     DataType
    0.06
     少
    0.06
     dates
    0.06
    #else
    0.06
    Activations Density 0.002%

    No Known Activations