© 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. 16320
    Prev
    Next
    INDEX
    Explanations

    references to locations and their significance

    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
    lyph
    -0.07
    odon
    -0.07
    onio
    -0.06
    ĭ
    -0.06
     staunch
    -0.06
     завиÑģим
    -0.06
    hdl
    -0.06
     Benn
    -0.06
     Hammer
    -0.06
     implicitly
    -0.06
    POSITIVE LOGITS
     ranks
    0.09
     become
    0.09
     rank
    0.09
     ÑıвлÑıеÑĤÑģÑı
    0.09
    æĪIJçĤº
    0.08
    æĺ¯æĪij
    0.08
    æĪIJ为
    0.08
    bec
    0.08
     becoming
    0.08
     regarded
    0.08
    Activations Density 0.114%

    No Known Activations