© 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. 61933
    Prev
    Next
    INDEX
    Explanations

    references to excitement and personal experiences related to activities or interactions

    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
    yw
    -0.07
    urring
    -0.06
    InProgress
    -0.06
    nota
    -0.06
    gue
    -0.06
    weg
    -0.06
    Ñıб
    -0.06
     tracked
    -0.06
     continued
    -0.06
    Persist
    -0.06
    POSITIVE LOGITS
     will
    0.09
     promises
    0.09
    will
    0.08
     promise
    0.07
     promising
    0.07
    expect
    0.07
     hopefully
    0.07
     excited
    0.07
     expect
    0.07
     excitement
    0.07
    Activations Density 0.071%

    No Known Activations