© 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. 39800
    Prev
    Next
    INDEX
    Explanations

    numerical references and citations related to scientific literature

    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
    nemonic
    -0.07
     pij
    -0.07
    orest
    -0.07
    ubyte
    -0.07
    urry
    -0.07
    inear
    -0.06
    igans
    -0.06
    ibri
    -0.06
    trx
    -0.06
    892
    -0.06
    POSITIVE LOGITS
    osten
    0.06
    chaft
    0.06
     Proceedings
    0.06
    ÏĥÏĦή
    0.06
    uth
    0.05
     vet
    0.05
    rea
    0.05
    abouts
    0.05
    unn
    0.05
     congress
    0.05
    Activations Density 0.010%

    No Known Activations