© 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. 76900
    Prev
    Next
    INDEX
    Explanations

    statistics and data related to environmental and resource conditions, particularly focusing on critical states and declines

    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
    \Exceptions
    -0.07
    èĢ³
    -0.07
    _lazy
    -0.06
    lund
    -0.06
    llib
    -0.06
    antan
    -0.06
     verst
    -0.06
    ORA
    -0.06
    _EXPR
    -0.06
    ÅĻÃŃ
    -0.06
    POSITIVE LOGITS
     potentially
    0.09
    pot
    0.07
     Potential
    0.07
     currently
    0.07
     Danger
    0.07
     dangerously
    0.07
    Lik
    0.07
     cand
    0.07
    ева
    0.07
     potential
    0.06
    Activations Density 0.018%

    No Known Activations