© 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. 88167
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    packages and libraries related to automated testing of applications.

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

    requests or discussions about programming/software topics—especially libraries, scripts, and technical issues—across multiple languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Same
    -0.06
    _OPER
    -0.06
     IDX
    -0.06
    $$$
    -0.06
     lacking
    -0.06
     Ge
    -0.06
     Vision
    -0.06
    .Persistent
    -0.06
    >Total
    -0.06
     Calibration
    -0.06
    POSITIVE LOGITS
    عاد
    0.08
    abeled
    0.07
     суду
    0.07
     faiz
    0.06
     nw
    0.06
    occus
    0.06
     Moines
    0.06
    िष
    0.06
    setStatus
    0.06
     paraph
    0.06
    Activations Density 0.248%

    No Known Activations