© 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 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. 119207
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts, particularly those indicating daytime

    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
    kaç
    -0.08
    çīĮ
    -0.07
    оÑĩек
    -0.07
     доÑĤ
    -0.07
    бин
    -0.07
    SSIP
    -0.07
    Ì
    -0.07
     èĹ
    -0.07
    ray
    -0.07
     INCIDENT
    -0.07
    POSITIVE LOGITS
    ime
    0.09
    enment
    0.07
     hours
    0.07
    mediate
    0.06
    657
    0.06
    rosse
    0.06
     powder
    0.06
     portion
    0.06
    onte
    0.06
    /full
    0.06
    Activations Density 0.005%

    No Known Activations