© 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. 15-LLAMASCOPE-RES-131K
    11. 87664
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    heel
    -0.07
    iga
    -0.06
    ARED
    -0.06
    Americ
    -0.06
    .fm
    -0.06
    648
    -0.06
     Coff
    -0.06
    borg
    -0.06
     Wagner
    -0.06
    igo
    -0.06
    POSITIVE LOGITS
     Oz
    0.06
     lanc
    0.06
    udeau
    0.06
     ends
    0.06
    phin
    0.06
    akens
    0.06
     Lots
    0.06
    ossier
    0.06
    pute
    0.06
    izon
    0.06
    Activations Density 0.000%

    No Known Activations