© 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. 125546
    Prev
    Next
    INDEX
    Explanations

    terms related to customer service and satisfaction

    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
    ekim
    -0.07
    umont
    -0.07
    éré
    -0.07
    ollo
    -0.06
    educt
    -0.06
    etooth
    -0.06
    deaux
    -0.06
    беÑĢ
    -0.06
    izzare
    -0.06
    vasive
    -0.06
    POSITIVE LOGITS
     alike
    0.09
    gba
    0.07
     excer
    0.07
    ortal
    0.07
    olet
    0.07
     RI
    0.06
     Klo
    0.06
    ιÏĩ
    0.06
    ersen
    0.06
    ì¹Ļ
    0.06
    Activations Density 0.021%

    No Known Activations