© 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. 4878
    Prev
    Next
    INDEX
    Explanations

    numeric representations or discussions surrounding statistics and financial values

    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
    usp
    -0.07
    ุà¹ī
    -0.07
    loha
    -0.06
    corner
    -0.06
    ãĥĨãĥ«
    -0.06
    nel
    -0.06
    achu
    -0.06
    note
    -0.06
    _Desc
    -0.06
    Mission
    -0.06
    POSITIVE LOGITS
     Advertisement
    0.07
     Ley
    0.07
     Anch
    0.06
     EDT
    0.06
    "It
    0.06
    ADVERTISEMENT
    0.06
    “It
    0.06
     anch
    0.06
     delt
    0.06
    anch
    0.06
    Activations Density 0.073%

    No Known Activations