© 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. 9-LLAMASCOPE-RES-131K
    11. 97154
    Prev
    Next
    INDEX
    Explanations

    German and French articles, pronouns, and definite 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
    hei
    -0.08
     éĤ
    -0.07
    úi
    -0.06
    herent
    -0.06
    -cigaret
    -0.06
    chie
    -0.06
    DAT
    -0.06
    dk
    -0.06
    ÑĪÑĮ
    -0.06
    ุà¹ī
    -0.06
    POSITIVE LOGITS
    olik
    0.07
    TEX
    0.07
    lesh
    0.07
    coles
    0.07
    adle
    0.07
    tring
    0.07
     Dreams
    0.07
    нила
    0.06
    lesen
    0.06
    ippers
    0.06
    Activations Density 0.015%

    No Known Activations