© 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. 104898
    Prev
    Next
    INDEX
    Explanations

    nouns and terms related to organizations, entities, and legal structures

    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
    aeda
    -0.07
    avid
    -0.07
    Bounding
    -0.07
    legg
    -0.07
    AZY
    -0.07
    anny
    -0.07
    _estimator
    -0.07
    zap
    -0.07
    iggers
    -0.07
    hone
    -0.07
    POSITIVE LOGITS
    819
    0.07
    arin
    0.07
    769
    0.07
    sp
    0.07
    ently
    0.06
    684
    0.06
    070
    0.06
    679
    0.06
    756
    0.06
     ·
    0.06
    Activations Density 0.028%

    No Known Activations