© 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. 106388
    Prev
    Next
    INDEX
    Explanations

    concepts related to cultural or historical 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
     artık
    -0.08
     again
    -0.08
    æĹ©
    -0.07
    åıĪ
    -0.07
     opÄĽt
    -0.07
     nue
    -0.07
     already
    -0.07
    already
    -0.07
    again
    -0.07
     novamente
    -0.07
    POSITIVE LOGITS
     remains
    0.10
     remain
    0.08
     retains
    0.08
     despite
    0.08
     spite
    0.07
     Plenty
    0.07
    ungan
    0.07
     masih
    0.07
    Despite
    0.07
     occasional
    0.07
    Activations Density 0.121%

    No Known Activations