© 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. 5058
    Prev
    Next
    INDEX
    Explanations

    special characters and JavaScript method definitions

    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
    enga
    -0.07
    Ì
    -0.07
    iga
    -0.06
    ono
    -0.06
    elong
    -0.06
    ">ÃĹ</
    -0.06
    owers
    -0.06
    521
    -0.06
    avigate
    -0.06
    433
    -0.06
    POSITIVE LOGITS
     rich
    0.07
     Rich
    0.07
    maz
    0.07
    aight
    0.07
    Rich
    0.06
    ãĥīãĥ«
    0.06
    sik
    0.06
     Baz
    0.06
    rich
    0.06
     bình
    0.06
    Activations Density 0.000%

    No Known Activations