© 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. 40220
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes or scenarios

    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
     whenever
    -0.08
    anticipated
    -0.07
    .scalablytyped
    -0.06
    WebResponse
    -0.06
    asper
    -0.06
     Apparently
    -0.06
    ĵį
    -0.06
    odb
    -0.06
     Whenever
    -0.06
     glyphicon
    -0.06
    POSITIVE LOGITS
     might
    0.15
     could
    0.14
     would
    0.13
    might
    0.12
    could
    0.11
    would
    0.11
     Might
    0.11
     могли
    0.10
     may
    0.10
     any
    0.10
    Activations Density 0.005%

    No Known Activations