© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41540
    Prev
    Next
    INDEX
    Explanations

    mentions of international organizations and agreements

    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
    моÑĤ
    -0.07
    oreach
    -0.06
    Ľi
    -0.06
    ENARIO
    -0.06
    ensa
    -0.06
     peoples
    -0.06
    ...
    -0.06
    ighbor
    -0.06
     eer
    -0.06
    eba
    -0.06
    POSITIVE LOGITS
     oneself
    0.07
     itself
    0.07
    vÄĽÅĻ
    0.07
     ìĿ´ëĬĶ
    0.07
    ÙĪÙĩ
    0.06
    Enlarge
    0.06
    ipur
    0.06
     manner
    0.06
    ÙĪØŃ
    0.06
     ello
    0.06
    Activations Density 0.000%

    No Known Activations