© 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. 125400
    Prev
    Next
    INDEX
    Explanations

    references to events, locations, and performance-related topics

    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
    ỳ
    -0.08
    plusplus
    -0.07
    ãģĤãĤĭ
    -0.07
     pent
    -0.06
     amat
    -0.06
    ifen
    -0.06
     nữa
    -0.06
    orgia
    -0.06
     zach
    -0.06
    pent
    -0.06
    POSITIVE LOGITS
     cannot
    0.14
     tidak
    0.12
    cannot
    0.12
     neither
    0.12
    æĹłæ³ķ
    0.11
     ÙĪÙĦÙħ
    0.11
     unlikely
    0.11
     no
    0.11
    ä¸įèĥ½
    0.11
     Cannot
    0.11
    Activations Density 0.075%

    No Known Activations