© 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. 87420
    Prev
    Next
    INDEX
    Explanations

    expressions of decision-making and realization

    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
    apid
    -0.09
    uem
    -0.07
    審
    -0.07
     desn
    -0.07
    cÃŃm
    -0.06
    occo
    -0.06
    彦
    -0.06
    ãĥ¼ãĥĸ
    -0.06
    unker
    -0.06
    INGTON
    -0.06
    POSITIVE LOGITS
     conclusion
    0.13
     concluded
    0.12
     finally
    0.12
     conclude
    0.11
     concludes
    0.10
     decided
    0.10
    finally
    0.10
     result
    0.10
     concl
    0.09
     Conclusion
    0.09
    Activations Density 0.042%

    No Known Activations