© 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. 62866
    Prev
    Next
    INDEX
    Explanations

    temporal references related to time durations

    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
    eto
    -0.07
    onto
    -0.07
    eton
    -0.07
     skew
    -0.07
    ataka
    -0.07
    unga
    -0.07
    Vu
    -0.07
    ouv
    -0.06
    267
    -0.06
     finer
    -0.06
    POSITIVE LOGITS
     Leigh
    0.07
     KN
    0.07
     ago
    0.06
    ?url
    0.06
     æ
    0.06
    aku
    0.06
    izzy
    0.06
     LENG
    0.06
    atur
    0.06
    ?id
    0.06
    Activations Density 0.002%

    No Known Activations