© 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. 70253
    Prev
    Next
    INDEX
    Explanations

    instances of user interface icons or indicators

    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
    isson
    -0.08
    ynos
    -0.07
    ieties
    -0.07
    zano
    -0.07
    uple
    -0.07
    ibel
    -0.07
    chsel
    -0.07
    abcdefghijkl
    -0.07
    incinn
    -0.06
    ='../
    -0.06
    POSITIVE LOGITS
    B
    0.06
     Peek
    0.06
     TAS
    0.06
     Cham
    0.06
    Fa
    0.06
    Ùıر
    0.06
    R
    0.06
    T
    0.06
    æĪIJ
    0.06
     passive
    0.06
    Activations Density 0.002%

    No Known Activations