© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60194
    Prev
    Next
    INDEX
    Explanations

    annotations related to nullability and privacy in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odon
    -0.07
    atro
    -0.06
    gos
    -0.06
    oe
    -0.06
    iod
    -0.06
    znik
    -0.06
     Ray
    -0.05
     Vand
    -0.05
     Radi
    -0.05
    论åĿĽ
    -0.05
    POSITIVE LOGITS
    icode
    0.07
    еж
    0.07
    .updateDynamic
    0.07
    parison
    0.07
     addCriterion
    0.06
    undra
    0.06
    |h
    0.06
     Khu
    0.06
    ãĥ³ãĥĸ
    0.06
    å¤ľ
    0.06
    Activations Density 0.001%

    No Known Activations