© 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. 17-LLAMASCOPE-RES-131K
    11. 40783
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and cultural references

    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
    atte
    -0.07
    eref
    -0.07
    oi
    -0.06
    ìĿ´ìŀIJ
    -0.06
     pornstar
    -0.06
     creampie
    -0.06
     incel
    -0.06
    ettings
    -0.06
    -fontawesome
    -0.06
     çat
    -0.06
    POSITIVE LOGITS
     amongst
    0.14
     among
    0.13
     etc
    0.13
    among
    0.12
     others
    0.10
    etc
    0.10
     Among
    0.10
    ãģªãģ©
    0.09
     respectively
    0.09
    çŃī
    0.09
    Activations Density 0.016%

    No Known Activations