© 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. 59408
    Prev
    Next
    INDEX
    Explanations

    links and resource 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
    Lastly
    -0.09
     Lastly
    -0.09
     finally
    -0.07
     Finally
    -0.06
    Finally
    -0.06
    岡
    -0.06
    адÑĥ
    -0.06
     Ion
    -0.06
     okum
    -0.06
     pur
    -0.06
    POSITIVE LOGITS
    odem
    0.07
    _Description
    0.07
    umbling
    0.07
    .Mode
    0.06
    ossil
    0.06
    vy
    0.06
    alam
    0.06
     saja
    0.06
    eren
    0.06
    ÏĩÏİ
    0.06
    Activations Density 0.011%

    No Known Activations