© 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. 15-LLAMASCOPE-RES-131K
    6. 89833
    Prev
    Next
    INDEX
    Explanations

    references to funding sources or financial support

    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
    ipes
    -0.07
    inel
    -0.07
    vell
    -0.07
    iginal
    -0.07
    cookies
    -0.07
    ardin
    -0.07
    erspective
    -0.07
    ulist
    -0.06
    tron
    -0.06
    CRET
    -0.06
    POSITIVE LOGITS
    yal
    0.06
    quito
    0.06
     conc
    0.06
     Working
    0.06
     Gross
    0.06
    yy
    0.06
    dad
    0.06
     Garrett
    0.06
    790
    0.06
     wax
    0.06
    Activations Density 0.001%

    No Known Activations