© 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. 81025
    Prev
    Next
    INDEX
    Explanations

    specific names, titles, or notable entities relevant to the context of discussion

    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
    ẽ
    -0.06
    andon
    -0.06
     Orthodox
    -0.06
     totiž
    -0.06
    cone
    -0.06
     Nah
    -0.06
    enson
    -0.06
    á»ħ
    -0.06
    озем
    -0.06
    ,exports
    -0.05
    POSITIVE LOGITS
     hadn
    0.08
     hasn
    0.08
    pite
    0.07
     nowhere
    0.07
     doesn
    0.07
     haven
    0.07
     didn
    0.07
     wasn
    0.07
     initially
    0.07
    333
    0.07
    Activations Density 0.036%

    No Known Activations