© 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. 81726
    Prev
    Next
    INDEX
    Explanations

    the import statements in code

    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
    ulas
    -0.07
    xn
    -0.07
    aepernick
    -0.07
    Äįer
    -0.07
    amarin
    -0.07
    ucle
    -0.07
    ForResult
    -0.07
    нÑĮ
    -0.07
     Dud
    -0.07
    GLOBALS
    -0.07
    POSITIVE LOGITS
     Ler
    0.07
    bjerg
    0.06
     Boom
    0.06
    bows
    0.06
    æĿ¿
    0.06
    -fw
    0.06
     Lay
    0.05
     Kemp
    0.05
    933
    0.05
     Äijô
    0.05
    Activations Density 0.000%

    No Known Activations