© 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. 56143
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases that highlight comparisons and distinctions

    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
    .gdx
    -0.07
     Hamp
    -0.06
    onth
    -0.06
    980
    -0.06
    clist
    -0.06
    =__
    -0.06
    Å¡ti
    -0.06
     Shard
    -0.06
    jspx
    -0.06
    ¶Į
    -0.06
    POSITIVE LOGITS
     difference
    0.12
    Difference
    0.11
    difference
    0.11
    å·®
    0.11
     differences
    0.10
     Difference
    0.10
     comparison
    0.10
    ifference
    0.09
    _difference
    0.08
     comparisons
    0.08
    Activations Density 0.001%

    No Known Activations