© 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. 62182
    Prev
    Next
    INDEX
    Explanations

    expressions explaining reasons or justifications

    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
     plais
    -0.07
    avenport
    -0.07
    aison
    -0.07
    ÏĦÏī
    -0.06
    ym
    -0.06
     mysl
    -0.06
    imeo
    -0.06
    yi
    -0.06
    UTES
    -0.06
    utas
    -0.06
    POSITIVE LOGITS
     it
    0.09
     It
    0.07
    å®ĥ
    0.07
    ersed
    0.07
    ï¼Įå®ĥ
    0.07
     once
    0.06
     forced
    0.06
     allows
    0.06
    Ŀi
    0.06
     Forces
    0.06
    Activations Density 0.033%

    No Known Activations