© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 118707
    Prev
    Next
    INDEX
    Explanations

    references to context and connection in programming or middleware processes

    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
    anou
    -0.07
    лаÑĤ
    -0.07
    illion
    -0.07
     обÑĭ
    -0.07
    eteor
    -0.07
    viar
    -0.06
    LOWER
    -0.06
     pii
    -0.06
    fax
    -0.06
    µ¬
    -0.06
    POSITIVE LOGITS
    327
    0.07
    inis
    0.07
    137
    0.07
    imat
    0.06
    357
    0.06
    ħn
    0.06
     punches
    0.06
    acula
    0.06
    lpVtbl
    0.05
    ìĿ´ìĬ¤
    0.05
    Activations Density 0.019%

    No Known Activations