© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68734
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric API version strings (dates in “YYYY-MM-DD” form) embedded in code or JSON.

    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
     Pessoa
    -0.07
    rier
    -0.06
     mechan
    -0.06
    errer
    -0.06
     Lon
    -0.06
    xAB
    -0.06
     oblig
    -0.06
    �
    -0.06
     mening
    -0.06
     PATH
    -0.06
    POSITIVE LOGITS
    ováno
    0.08
    成為
    0.06
    (TreeNode
    0.06
    ujemy
    0.06
     skutečně
    0.06
    .groupControl
    0.06
     Toyota
    0.06
    <<<<<<<<
    0.06
    fty
    0.06
    ภาพยนตร
    0.06
    Activations Density 0.002%

    No Known Activations