© 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. 107401
    Prev
    Next
    INDEX
    Explanations

    mentions of specific symbols or abbreviations related to physical quantities or measurements

    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
    s
    -0.08
    .googlecode
    -0.07
    ary
    -0.06
    aire
    -0.06
    ervices
    -0.06
     Fate
    -0.06
    \Migrations
    -0.06
    S
    -0.06
    788
    -0.06
    ergy
    -0.06
    POSITIVE LOGITS
    212
    0.07
    ümÃ¼ÅŁ
    0.07
    ullo
    0.07
    bow
    0.07
    ç¤
    0.07
    swire
    0.07
    воÑİ
    0.07
    ÑĪкÑĥ
    0.07
    ÙĦس
    0.07
    illance
    0.07
    Activations Density 0.010%

    No Known Activations