© 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 EvalsExportsAPI 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. 77143
    Prev
    Next
    INDEX
    Explanations

    information about a specific product or solution

    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
     phenomenon
    -0.07
     Lamb
    -0.06
     Eg
    -0.06
     nast
    -0.06
     ps
    -0.06
     phenomena
    -0.06
    adian
    -0.06
    zer
    -0.06
    sp
    -0.06
    ingly
    -0.06
    POSITIVE LOGITS
    ãģĵãģ¡ãĤī
    0.10
    à¥ī
    0.07
    aga
    0.07
     @$_
    0.07
    ERRUPT
    0.07
    otec
    0.07
     ØŃض
    0.07
    ãĤ¤ãĤº
    0.07
    @js
    0.07
    ENSOR
    0.07
    Activations Density 0.004%

    No Known Activations