© 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. 15-LLAMASCOPE-RES-131K
    11. 87749
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational resources and information dissemination

    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
    ês
    -0.06
     pr
    -0.06
     f
    -0.06
     right
    -0.06
    .GetInstance
    -0.06
     even
    -0.06
     italic
    -0.05
     new
    -0.05
     IM
    -0.05
    YST
    -0.05
    POSITIVE LOGITS
     Redistributions
    0.09
    ADVERTISEMENT
    0.07
    лÑİд
    0.07
    jak
    0.07
     thôi
    0.07
     tâm
    0.07
    ITUDE
    0.07
    ¦Ĥ
    0.07
     PROVIDED
    0.07
    å±±å¸Ĥ
    0.07
    Activations Density 0.015%

    No Known Activations