© 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. 41392
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight connections and comparisons among different concepts or entities

    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
     vs
    -0.07
    vers
    -0.07
     Ry
    -0.06
     lâu
    -0.06
    vs
    -0.06
    -vs
    -0.06
     доÑĢ
    -0.06
     Ell
    -0.06
    lfw
    -0.06
     ä¸İ
    -0.05
    POSITIVE LOGITS
     alike
    0.15
     respectively
    0.11
    缸åIJĮ
    0.10
     respective
    0.10
    ä¸Ģæł·
    0.09
     identical
    0.09
    åĪĨåĪ«
    0.09
    same
    0.09
     complementary
    0.08
    åIJĮ
    0.08
    Activations Density 0.064%

    No Known Activations