© 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. 9-LLAMASCOPE-RES-131K
    11. 94532
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and their formatting

    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
    enant
    -0.07
    anton
    -0.06
    @qq
    -0.06
    ached
    -0.06
     newObj
    -0.06
    adian
    -0.06
    ansi
    -0.06
    rophe
    -0.06
    ng
    -0.06
    rollo
    -0.06
    POSITIVE LOGITS
    ednou
    0.07
    FINITY
    0.07
     å·Ŀ
    0.07
    694
    0.07
    LEGRO
    0.07
    jeme
    0.07
    etsy
    0.07
    ApplicationBuilder
    0.07
    inger
    0.06
    allen
    0.06
    Activations Density 0.053%

    No Known Activations