© 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. 73302
    Prev
    Next
    INDEX
    Explanations

    references to blog posts and links related to visual content or design

    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
    dea
    -0.07
    ammad
    -0.06
    112
    -0.06
     div
    -0.06
    osaic
    -0.06
     enrich
    -0.05
    tle
    -0.05
     Congress
    -0.05
     Minor
    -0.05
    ammed
    -0.05
    POSITIVE LOGITS
    ingo
    0.08
    Äįin
    0.07
    icÃŃ
    0.07
    /copyleft
    0.07
    aylight
    0.07
    å¾Ħ
    0.06
    forge
    0.06
    avra
    0.06
     microtime
    0.06
    à¹ĩà¸Ńà¸ķ
    0.06
    Activations Density 0.001%

    No Known Activations