© 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. 28225
    Prev
    Next
    INDEX
    Explanations

    words related to various languages or translations

    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
    کر
    -0.08
    برÛĮ
    -0.07
    engl
    -0.07
    Ñĩем
    -0.07
    Äįan
    -0.07
    plusplus
    -0.07
    بر
    -0.07
    loha
    -0.07
     arac
    -0.07
    Æ°ng
    -0.06
    POSITIVE LOGITS
    chn
    0.07
    /or
    0.07
    -Semit
    0.07
    ième
    0.07
    redients
    0.06
    åľ°æĸ¹
    0.06
     gn
    0.06
    /epl
    0.06
    -than
    0.06
    ix
    0.06
    Activations Density 0.067%

    No Known Activations