© 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. 73626
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles

    np_max-act · gemini-2.0-flash

    instances of funding related to foreign contracting in government reports.

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

    The neuron activates on decimal number tokens representing fractional values (floating-point literals).

    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
    ガ
    -0.07
    АР
    -0.07
    DEN
    -0.07
    요
    -0.07
     thesis
    -0.06
     văn
    -0.06
     Cran
    -0.06
     Rope
    -0.06
    je
    -0.06
    den
    -0.06
    POSITIVE LOGITS
    -custom
    0.07
    struct
    0.06
    _crc
    0.06
    Suggestions
    0.06
    .tableLayoutPanel
    0.06
     touch
    0.06
     What
    0.06
    нання
    0.06
     sincerely
    0.06
     setuptools
    0.06
    Activations Density 0.283%

    No Known Activations