© 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. 123704
    Prev
    Next
    INDEX
    Explanations

    connections and relationships among various subjects or entities

    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
     subur
    -0.07
    obar
    -0.07
    åĩºåİ»
    -0.07
    vero
    -0.07
    bard
    -0.06
    ç¦
    -0.06
    oble
    -0.06
     XCT
    -0.06
    byname
    -0.06
    æĭ©
    -0.06
    POSITIVE LOGITS
     both
    0.27
    both
    0.25
     BOTH
    0.23
    Both
    0.22
     Both
    0.22
    _both
    0.19
     både
    0.18
     ambos
    0.17
     beide
    0.17
     обо
    0.16
    Activations Density 0.065%

    No Known Activations