© 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. 86789
    Prev
    Next
    INDEX
    Explanations

    expressions of knowledge and understanding

    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
    ukan
    -0.08
    æ¡
    -0.08
    .sponge
    -0.07
    ez
    -0.07
    mc
    -0.07
    ochrome
    -0.07
    ron
    -0.07
    imary
    -0.07
    .Business
    -0.06
    raud
    -0.06
    POSITIVE LOGITS
     rằng
    0.07
     there
    0.07
     that
    0.07
    Sensitive
    0.06
    75
    0.06
    elic
    0.06
    Łèĥ½
    0.06
    CAPE
    0.06
    ãĤ¤ãĤº
    0.06
     Guar
    0.06
    Activations Density 0.017%

    No Known Activations