© 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. 87889
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "OS" and its variations in a technical context

    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
     Cros
    -0.07
    andard
    -0.07
    inct
    -0.07
    imli
    -0.07
    addock
    -0.07
    adge
    -0.07
    elden
    -0.07
    Trait
    -0.06
    nees
    -0.06
    hos
    -0.06
    POSITIVE LOGITS
    Ø°
    0.06
     eventual
    0.06
    ests
    0.06
     Flight
    0.06
    æ¼Ĥ
    0.05
    èŃ
    0.05
    plits
    0.05
     بÙĦ
    0.05
    iskey
    0.05
    CTS
    0.05
    Activations Density 0.001%

    No Known Activations