© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71613
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities

    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
    s
    -0.14
    ñana
    -0.08
    sar
    -0.08
    sak
    -0.08
    spr
    -0.07
    âĢ²
    -0.07
    PÅĻi
    -0.07
    utenant
    -0.07
    sburg
    -0.07
    aley
    -0.07
    POSITIVE LOGITS
    fold
    0.09
    quel
    0.06
    gue
    0.06
    emme
    0.06
    oxel
    0.06
    ancy
    0.06
    .esp
    0.06
    idian
    0.06
    naire
    0.06
    -first
    0.06
    Activations Density 0.013%

    No Known Activations