© 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. 29352
    Prev
    Next
    INDEX
    Explanations

    dates and numerical values related to events or information

    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
    iami
    -0.06
    .Apis
    -0.06
    undry
    -0.06
    MOTE
    -0.06
    ingly
    -0.06
     Bros
    -0.06
    udos
    -0.06
    alus
    -0.06
    atum
    -0.06
    .shtml
    -0.06
    POSITIVE LOGITS
    interop
    0.07
    ä¸Ī
    0.07
    /fw
    0.07
     Coll
    0.06
     ÑĢаÑħ
    0.06
    .scalablytyped
    0.06
    æĭ©
    0.06
     oblig
    0.06
    RowIndex
    0.06
    ewire
    0.06
    Activations Density 0.002%

    No Known Activations