© 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. 28139
    Prev
    Next
    INDEX
    Explanations

    references to the camp Pemi

    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
    ICI
    -0.07
    žit
    -0.07
    quent
    -0.06
    ÃŃÅĻ
    -0.06
    ipop
    -0.06
    orado
    -0.06
    forge
    -0.06
    occo
    -0.06
    apur
    -0.06
    erli
    -0.06
    POSITIVE LOGITS
    »
    0.06
     Españ
    0.06
    ÂĿ
    0.06
    donnees
    0.06
    ĶåĽŀ
    0.06
    /Instruction
    0.06
    atics
    0.06
    ului
    0.05
    çļĦå£°éŁ³
    0.05
    ाà¤Ĭ
    0.05
    Activations Density 0.128%

    No Known Activations