© 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. 38811
    Prev
    Next
    INDEX
    Explanations

    dates and times in the text

    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
    oter
    -0.06
    ota
    -0.06
    IMIT
    -0.06
    qm
    -0.06
     trace
    -0.06
    avis
    -0.06
    ROWSER
    -0.06
    iju
    -0.06
    {text
    -0.06
     parte
    -0.06
    POSITIVE LOGITS
    Reply
    0.06
    PLIED
    0.06
     Kirst
    0.06
    odal
    0.06
    _TP
    0.06
    ihan
    0.06
    abella
    0.06
    371
    0.06
    olic
    0.06
    tester
    0.06
    Activations Density 0.018%

    No Known Activations