© 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. 15-LLAMASCOPE-RES-131K
    11. 1517
    Prev
    Next
    INDEX
    Explanations

    descriptors that convey qualities of products, experiences, or characteristics

    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
    tran
    -0.07
    atee
    -0.07
    chine
    -0.06
    udu
    -0.06
    aterno
    -0.06
    asin
    -0.06
    ables
    -0.06
    resi
    -0.06
    AGR
    -0.06
    atro
    -0.06
    POSITIVE LOGITS
     enough
    0.10
    actly
    0.07
    ValueCollection
    0.07
    ually
    0.07
    istically
    0.07
    edBy
    0.07
    astically
    0.07
    ically
    0.07
    ently
    0.07
    ologically
    0.07
    Activations Density 0.091%

    No Known Activations