© 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. 106651
    Prev
    Next
    INDEX
    Explanations

    numerical data and figures related to scientific measurements or calculations

    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
    isle
    -0.08
    utches
    -0.08
    rug
    -0.08
    oa
    -0.07
    leg
    -0.07
    edom
    -0.07
    @yahoo
    -0.06
    ürnberg
    -0.06
    PathComponent
    -0.06
    udos
    -0.06
    POSITIVE LOGITS
    -widgets
    0.07
     {{--<
    0.07
    ãĥĨãĥ«
    0.07
    (æĹ¥
    0.07
    -ln
    0.07
    ]){
    0.06
    /embed
    0.06
    (æ°´
    0.06
    ï¼į
    0.06
     condition
    0.06
    Activations Density 0.004%

    No Known Activations