© 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. 15600
    Prev
    Next
    INDEX
    Explanations

    words related to languages or linguistic 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
    eft
    -0.07
    ynchronize
    -0.07
    stocks
    -0.07
    ây
    -0.07
    woo
    -0.07
    quin
    -0.07
    ariate
    -0.07
    uy
    -0.06
    flies
    -0.06
    ucer
    -0.06
    POSITIVE LOGITS
    :
    0.09
     NhÆ°
    0.06
     render
    0.06
     Wik
    0.06
     Affero
    0.06
    ullah
    0.06
    usan
    0.06
     ÙĪÛĮÚ©ÛĮ
    0.06
    ldr
    0.06
    soever
    0.05
    Activations Density 0.005%

    No Known Activations