© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 864
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to systems of control and technical excellence

    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
    zek
    -0.08
    aghan
    -0.08
    odor
    -0.07
     milan
    -0.07
    аки
    -0.07
    bek
    -0.07
    kee
    -0.07
    clid
    -0.06
    lef
    -0.06
    endo
    -0.06
    POSITIVE LOGITS
    CursorPosition
    0.07
    ymes
    0.07
     ÑģÑĤаÑĤи
    0.06
     diff
    0.06
     patent
    0.06
    UGIN
    0.06
    ůr
    0.06
    lags
    0.06
    ÐŁÐļ
    0.06
    ynes
    0.06
    Activations Density 0.000%

    No Known Activations