© 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. 28832
    Prev
    Next
    INDEX
    Explanations

    aspects of travel, hospitality, and economic data

    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
    olley
    -0.07
    ìĪł
    -0.07
    esi
    -0.07
    elles
    -0.07
    ocht
    -0.06
    apore
    -0.06
    udget
    -0.06
    akh
    -0.06
    ctica
    -0.06
     here
    -0.06
    POSITIVE LOGITS
    ube
    0.07
    arat
    0.06
    Ĥæķ°
    0.06
    еÑĢк
    0.06
     Craig
    0.06
    rome
    0.06
     bindActionCreators
    0.06
    aro
    0.06
    uve
    0.06
    uhl
    0.06
    Activations Density 0.010%

    No Known Activations