© 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. 31015
    Prev
    Next
    INDEX
    Explanations

    terms related to biotechnology and scientific advancements

    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
    stroy
    -0.07
    uien
    -0.07
     anale
    -0.07
    .bz
    -0.07
    InstanceOf
    -0.07
    abant
    -0.07
    fos
    -0.07
    anca
    -0.06
    lech
    -0.06
    vant
    -0.06
    POSITIVE LOGITS
     platform
    0.09
     Platform
    0.08
    Platform
    0.08
    technology
    0.07
    library
    0.07
     PLATFORM
    0.07
     technology
    0.07
    platform
    0.07
    validated
    0.06
    PLATFORM
    0.06
    Activations Density 0.012%

    No Known Activations