© 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. 9-LLAMASCOPE-RES-131K
    11. 97010
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and institutions

    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
    avir
    -0.07
    bjerg
    -0.06
    OrUpdate
    -0.06
    uro
    -0.06
    微软éĽħé»ij
    -0.06
    chter
    -0.06
    aga
    -0.06
    WithContext
    -0.06
    IODevice
    -0.06
    uze
    -0.06
    POSITIVE LOGITS
     starttime
    0.07
    ież
    0.07
    invisible
    0.07
    iliz
    0.07
    etiyle
    0.07
    ADM
    0.06
    Ðĩ
    0.06
    .datasets
    0.06
    ấy
    0.06
     gardens
    0.06
    Activations Density 0.002%

    No Known Activations