© 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. 9-LLAMASCOPE-RES-131K
    11. 98073
    Prev
    Next
    INDEX
    Explanations

    timestamps and date formats 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
    bourg
    -0.07
    ogue
    -0.07
    bia
    -0.07
    anke
    -0.06
    urg
    -0.06
    placement
    -0.06
    win
    -0.06
    ishi
    -0.06
    ãģĪ
    -0.06
    arin
    -0.06
    POSITIVE LOGITS
    /REC
    0.07
    à¹īว
    0.07
    ائ
    0.07
    tul
    0.07
    ÑĢиÑĦ
    0.07
    REA
    0.07
    /documents
    0.07
     ninh
    0.07
    aat
    0.07
    aco
    0.07
    Activations Density 0.007%

    No Known Activations