© 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. 106311
    Prev
    Next
    INDEX
    Explanations

    the modal verb "can" indicating capability or possibility

    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
    ogram
    -0.07
    putation
    -0.07
    airo
    -0.06
    olia
    -0.06
    éric
    -0.06
    aurus
    -0.06
    roperty
    -0.06
    ç
    -0.06
    und
    -0.06
    .fm
    -0.06
    POSITIVE LOGITS
     also
    0.10
    either
    0.09
     either
    0.09
     freely
    0.08
    Also
    0.08
    also
    0.08
     Also
    0.08
     then
    0.07
    Either
    0.07
     Either
    0.07
    Activations Density 0.022%

    No Known Activations