© 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. 94902
    Prev
    Next
    INDEX
    Explanations

    timestamps and date references

    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
     kles
    -0.07
    uelle
    -0.06
    .gstatic
    -0.06
    onia
    -0.06
    .Reporting
    -0.06
    usercontent
    -0.06
    volt
    -0.06
    .dw
    -0.06
    weetalert
    -0.06
    _rq
    -0.06
    POSITIVE LOGITS
    å·¥æ¥Ń
    0.07
    ode
    0.07
    zimmer
    0.07
    anc
    0.06
     ordinances
    0.06
    hazi
    0.06
    ivan
    0.06
    ampa
    0.06
     ä¸ĸ
    0.06
    à¥ĭद
    0.06
    Activations Density 0.005%

    No Known Activations