© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential solutions or outcomes

    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
     kims
    -0.07
    ấp
    -0.06
     Odds
    -0.06
    æ¯
    -0.06
    essen
    -0.06
    oda
    -0.06
    assa
    -0.06
    setId
    -0.06
    _ENSURE
    -0.06
    _sd
    -0.06
    POSITIVE LOGITS
    /current
    0.08
     future
    0.07
    y
    0.07
    /pro
    0.07
    weise
    0.07
    ;y
    0.07
    ily
    0.07
     imminent
    0.07
     scenarios
    0.07
    mente
    0.07
    Activations Density 0.012%

    No Known Activations