© 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. 57441
    Prev
    Next
    INDEX
    Explanations

    references to events and positions related to time and festivals

    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
     wrong
    -0.06
    905
    -0.06
     cardio
    -0.06
    anik
    -0.05
     em
    -0.05
    ;
    -0.05
     Tome
    -0.05
    ess
    -0.05
     i
    -0.05
     filler
    -0.05
    POSITIVE LOGITS
     âĢª
    0.10
    _Tis
    0.09
    _mD
    0.09
    dül
    0.09
    aan
    0.09
    _mB
    0.08
    ekim
    0.08
    _mC
    0.08
    _mE
    0.08
    anken
    0.08
    Activations Density 0.001%

    No Known Activations