© 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. 60918
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to research processes and their findings

    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
    ["$
    -0.07
     thus
    -0.06
     dabei
    -0.06
    /or
    -0.06
    hack
    -0.06
     daher
    -0.06
    .getInstance
    -0.06
    chia
    -0.06
    wig
    -0.06
    stown
    -0.06
    POSITIVE LOGITS
     же
    0.10
    -ÑĤо
    0.10
    forth
    0.08
    czas
    0.08
    ETO
    0.08
    że
    0.08
     stesso
    0.07
    ä¹İ
    0.07
    curity
    0.07
    gorit
    0.07
    Activations Density 0.011%

    No Known Activations