© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84742
    Prev
    Next
    INDEX
    Explanations

    terminology related to screws and related mechanical concepts

    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
    oot
    -0.07
    .Dispatch
    -0.06
    ymous
    -0.06
    неÑģ
    -0.06
     Roose
    -0.06
    ottes
    -0.06
    amd
    -0.06
    zers
    -0.06
    hoo
    -0.06
    hu
    -0.06
    POSITIVE LOGITS
    driver
    0.11
    drivers
    0.09
    fish
    0.07
    orgia
    0.06
    enstein
    0.06
     lượng
    0.06
    edback
    0.06
    enberg
    0.06
    edish
    0.06
    jack
    0.06
    Activations Density 0.004%

    No Known Activations