© 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. 41750
    Prev
    Next
    INDEX
    Explanations

    temporal references and seasonal 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
     or
    -0.07
     neutral
    -0.07
    iples
    -0.06
    ↵
    -0.06
    ,
    -0.06
    hyth
    -0.06
     del
    -0.06
     nearest
    -0.06
    fest
    -0.06
     bet
    -0.06
    POSITIVE LOGITS
    olen
    0.09
    /Peak
    0.08
     ìĿ´ìłľ
    0.08
     tomorrow
    0.08
    /WebAPI
    0.08
    à¤ħब
    0.08
    ota
    0.07
    _tF
    0.07
    uzzi
    0.07
     SÆ¡n
    0.07
    Activations Density 0.034%

    No Known Activations