© 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. 29331
    Prev
    Next
    INDEX
    Explanations

    nouns related to tools and equipment

    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
    uitka
    -0.08
    ÙĪØŃ
    -0.08
     millenn
    -0.07
    thon
    -0.07
    aliz
    -0.07
    RAP
    -0.07
     scape
    -0.07
    rana
    -0.07
    ecko
    -0.07
    ?family
    -0.07
    POSITIVE LOGITS
    esto
    0.07
    olar
    0.06
     cum
    0.06
    ings
    0.06
     Kum
    0.06
     attachment
    0.06
    -equipped
    0.06
    ede
    0.06
    ulator
    0.06
    สำหร
    0.06
    Activations Density 0.050%

    No Known Activations