© 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. 105766
    Prev
    Next
    INDEX
    Explanations

    references to threading concepts in programming

    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
    нож
    -0.07
    laÅŁ
    -0.07
    ÙĦÙĬÙĩ
    -0.07
    spath
    -0.07
    indsight
    -0.07
    ãn
    -0.07
    avax
    -0.06
    shapes
    -0.06
     Laz
    -0.06
    .cx
    -0.06
    POSITIVE LOGITS
    .Tasks
    0.09
    ätt
    0.06
     Bbw
    0.06
    oyal
    0.06
     CONSEQUENTIAL
    0.06
    avÄĽ
    0.05
    Docs
    0.05
    TargetException
    0.05
    kees
    0.05
     Bik
    0.05
    Activations Density 0.000%

    No Known Activations