© 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. 81304
    Prev
    Next
    INDEX
    Explanations

    references to the concept of time

    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
     /^(
    -0.08
    headed
    -0.07
    á»Ļn
    -0.07
    nova
    -0.07
     Glover
    -0.07
    ìĹŃ
    -0.07
    jerne
    -0.07
     entitlement
    -0.06
    opa
    -0.06
    ruz
    -0.06
    POSITIVE LOGITS
     inf
    0.06
     sem
    0.06
     jud
    0.06
     Dw
    0.06
     Stap
    0.06
    ini
    0.06
    -tm
    0.06
    INST
    0.06
     sag
    0.06
    iddi
    0.06
    Activations Density 0.002%

    No Known Activations