© 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. 81799
    Prev
    Next
    INDEX
    Explanations

    numeric values and specific scientific 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
    ording
    -0.07
    akra
    -0.07
    ordova
    -0.06
    eras
    -0.06
    886
    -0.06
    lesi
    -0.06
    upertino
    -0.06
    esch
    -0.06
     Lang
    -0.06
    onical
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.08
     pp
    0.07
    .issue
    0.06
    оÑĢÑĤÑĥ
    0.06
    vyk
    0.06
    меÑĤÑĮ
    0.06
    htm
    0.06
    Ahead
    0.06
     stranÄĽ
    0.06
     ëĵ¯
    0.06
    Activations Density 0.016%

    No Known Activations