© 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. 9-LLAMASCOPE-RES-131K
    11. 97961
    Prev
    Next
    INDEX
    Explanations

    numeric representations or mentions of measurements and statistical data

    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
    que
    -0.08
    idel
    -0.07
    idle
    -0.07
    /cal
    -0.07
    aga
    -0.06
    ved
    -0.06
     Whit
    -0.06
    istra
    -0.06
     whit
    -0.06
     Morr
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĩ
    0.08
    -thumbnails
    0.08
    kyt
    0.07
     objc
    0.07
    ¢
    0.07
    å¯Ŀ
    0.07
    uger
    0.07
    ayette
    0.07
    ãĥ¼ãĥĭ
    0.07
    æ³½
    0.07
    Activations Density 0.003%

    No Known Activations