© 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. 71771
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols indicating the structure of 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
    inder
    -0.06
    mi
    -0.06
    l
    -0.06
    ot
    -0.06
    al
    -0.06
     rep
    -0.06
     fun
    -0.06
     par
    -0.06
    ur
    -0.05
    ub
    -0.05
    POSITIVE LOGITS
    ÏĦεÏħ
    0.07
    xima
    0.07
    .dy
    0.07
     svob
    0.07
    央
    0.07
     Jaune
    0.07
     UCHAR
    0.07
     porr
    0.07
    AsyncResult
    0.07
    ież
    0.07
    Activations Density 0.004%

    No Known Activations