© 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. 54573
    Prev
    Next
    INDEX
    Explanations

    formatting symbols and punctuation in text

    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
    chw
    -0.08
    jišť
    -0.08
    iani
    -0.07
    ابÛĮ
    -0.07
    endum
    -0.07
    enton
    -0.07
    vron
    -0.07
    erb
    -0.07
     latter
    -0.07
    ystate
    -0.07
    POSITIVE LOGITS
    s
    0.07
    udi
    0.07
    0.07
    bcm
    0.06
    ا
    0.06
    tsy
    0.06
    âĢİ
    0.06
     Levy
    0.06
     Schro
    0.06
    esters
    0.06
    Activations Density 0.086%

    No Known Activations