© 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 EvalsExportsinterp-engineNEWAPI 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. 73706
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and technical terms

    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
    üss
    -0.07
    upy
    -0.07
    (EXPR
    -0.07
    AWN
    -0.07
    رÙĪ
    -0.07
    .Throws
    -0.06
    pus
    -0.06
     epoll
    -0.06
     IPV
    -0.06
    (http
    -0.06
    POSITIVE LOGITS
    "
    0.06
    istro
    0.06
    riott
    0.06
    ancia
    0.05
    :
    0.05
     '
    0.05
    .
    0.05
    erk
    0.05
    Ī
    0.05
    ieder
    0.05
    Activations Density 0.083%

    No Known Activations