© 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. 9-LLAMASCOPE-RES-131K
    11. 94634
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with brands and specific products or technologies

    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
    mime
    -0.06
    ungan
    -0.06
    ipeg
    -0.06
    ãĤ¤ãĥĪ
    -0.06
    Ïħγ
    -0.06
    elow
    -0.06
    rig
    -0.06
    Locator
    -0.06
    uro
    -0.06
    arena
    -0.06
    POSITIVE LOGITS
     célib
    0.07
     porr
    0.06
    cour
    0.06
    fts
    0.06
     إد
    0.06
    .ico
    0.06
     Sanders
    0.06
    lett
    0.06
    krát
    0.06
    RU
    0.06
    Activations Density 0.009%

    No Known Activations