© 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. 92745
    Prev
    Next
    INDEX
    Explanations

    patterns and sequences related to numerical data and classifications

    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
    одо
    -0.07
     IID
    -0.06
     sce
    -0.06
    нÑĤ
    -0.06
    ucken
    -0.06
    ([...
    -0.06
    .sf
    -0.06
     quel
    -0.06
     Tec
    -0.06
    ữu
    -0.06
    POSITIVE LOGITS
    undy
    0.08
    æľĢåĪĿ
    0.08
     McCl
    0.08
    erot
    0.07
     inaugural
    0.07
     inicial
    0.07
    åĪĿ
    0.07
     Lamp
    0.07
    ept
    0.07
    mund
    0.07
    Activations Density 0.005%

    No Known Activations