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

    Neuronpedia

    Jacobian LensNEW
    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. 87552
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and elements

    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
     Flo
    -0.06
    ↵
    -0.06
    arium
    -0.06
    oute
    -0.05
    oron
    -0.05
    ummies
    -0.05
    bilt
    -0.05
     Knight
    -0.05
    ean
    -0.05
    iere
    -0.05
    POSITIVE LOGITS
    lassen
    0.08
    icter
    0.08
    edio
    0.07
    peg
    0.07
    icas
    0.07
    adow
    0.07
    icator
    0.07
    irut
    0.07
    maal
    0.07
    ettel
    0.07
    Activations Density 0.000%

    No Known Activations