© 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. 30665
    Prev
    Next
    INDEX
    Explanations

    numerical and date-based information related to geographic and historical contexts

    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
    éī
    -0.06
    Reviewed
    -0.05
    imax
    -0.05
     Tome
    -0.05
    uhan
    -0.05
    伯
    -0.05
    prene
    -0.05
    δÏİ
    -0.05
    ibre
    -0.05
     [&
    -0.05
    POSITIVE LOGITS
     Wikipedia
    0.11
    .wikipedia
    0.11
     wikipedia
    0.10
    /wiki
    0.10
    wiki
    0.09
    Wiki
    0.09
    ikipedia
    0.09
    https
    0.08
     Wiki
    0.08
     wiki
    0.08
    Activations Density 0.083%

    No Known Activations