© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    terms associated with historical events or periods

    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
     themselves
    -0.09
    esters
    -0.08
     zich
    -0.08
     herself
    -0.07
     mình
    -0.07
     himself
    -0.07
    Ïīν
    -0.07
    ÑĪиÑģÑĮ
    -0.07
     oneself
    -0.06
     sich
    -0.06
    POSITIVE LOGITS
    ing
    0.09
    ende
    0.09
     ing
    0.06
    ãģ¡ãģ¯
    0.06
    /w
    0.06
    leen
    0.06
    enth
    0.06
    ãģķãģĽ
    0.06
    ãģķãģĽãĤĭ
    0.06
    ìĦ¼
    0.06
    Activations Density 0.062%

    No Known Activations