© 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. 118423
    Prev
    Next
    INDEX
    Explanations

    emotive interjections and expressions of personal sentiment

    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
    ira
    -0.08
    avir
    -0.07
    ephir
    -0.07
    anship
    -0.07
    HomeController
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.07
    errated
    -0.07
    cean
    -0.07
    ivar
    -0.07
    ereco
    -0.07
    POSITIVE LOGITS
     sue
    0.10
     Sue
    0.09
     justification
    0.07
     blame
    0.07
     fault
    0.07
     suit
    0.07
    chalk
    0.06
    kan
    0.06
     shut
    0.06
     justified
    0.06
    Activations Density 0.054%

    No Known Activations