© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129937
    Prev
    Next
    INDEX
    Explanations

    references to programming and technical code elements

    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
    .mozilla
    -0.07
     Kling
    -0.06
     Nationwide
    -0.06
    undance
    -0.06
    uler
    -0.06
    uzz
    -0.06
    wyn
    -0.05
    uner
    -0.05
    aria
    -0.05
     Klopp
    -0.05
    POSITIVE LOGITS
     Phoenix
    0.07
    reno
    0.07
    .gdx
    0.07
    Phoenix
    0.07
     Graves
    0.07
    ë²Ķ
    0.07
    TES
    0.06
    erville
    0.06
    ocaly
    0.06
    iazza
    0.06
    Activations Density 0.056%

    No Known Activations