© 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. 30911
    Prev
    Next
    INDEX
    Explanations

    temporal markers and references to significant events

    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
     mez
    -0.06
     seasonal
    -0.06
     Sunrise
    -0.06
    orns
    -0.06
     Midnight
    -0.05
    orate
    -0.05
    stands
    -0.05
    ylon
    -0.05
     Rings
    -0.05
    zim
    -0.05
    POSITIVE LOGITS
    igne
    0.08
     day
    0.08
    ambi
    0.07
    ÅĻad
    0.07
    _ptrs
    0.07
     yesterday
    0.07
     Thursday
    0.07
    ProcessEvent
    0.07
     Wednesday
    0.07
     Monday
    0.07
    Activations Density 0.056%

    No Known Activations