© 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. 124597
    Prev
    Next
    INDEX
    Explanations

    references to archaeological findings and human remains

    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
    podob
    -0.07
    amerate
    -0.07
     sns
    -0.06
    å·
    -0.06
    ewise
    -0.06
     ingredient
    -0.06
    jÃŃž
    -0.06
     pen
    -0.06
    ixin
    -0.06
     neighborhoods
    -0.06
    POSITIVE LOGITS
     bones
    0.08
    corp
    0.07
     bone
    0.07
    apos
    0.07
     Clothing
    0.07
     oss
    0.07
    Ļ
    0.07
    arna
    0.06
     fem
    0.06
    osten
    0.06
    Activations Density 0.008%

    No Known Activations