© 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. 15-LLAMASCOPE-RES-131K
    11. 90076
    Prev
    Next
    INDEX
    Explanations

    references to the word "current."

    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
    ial
    -0.06
    alm
    -0.06
    ús
    -0.06
    ôt
    -0.06
    edd
    -0.06
     respectively
    -0.06
     respective
    -0.06
    Ñıд
    -0.06
     rounding
    -0.06
    plotlib
    -0.06
    POSITIVE LOGITS
     Current
    0.07
    ENSITY
    0.06
     durumda
    0.06
    ForMember
    0.06
    etooth
    0.06
    Version
    0.06
    chio
    0.06
    аÑĪа
    0.06
    version
    0.06
     Currently
    0.06
    Activations Density 0.024%

    No Known Activations