© 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. 94534
    Prev
    Next
    INDEX
    Explanations

    semicolons and quotations

    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
    etry
    -0.07
    kus
    -0.07
    lenÃŃ
    -0.06
    dbus
    -0.06
    ystems
    -0.06
     Reading
    -0.06
    usu
    -0.06
    903
    -0.06
    isé
    -0.06
     caul
    -0.06
    POSITIVE LOGITS
    .inline
    0.07
    airo
    0.06
    ritel
    0.06
    Ø®Ùħ
    0.06
    íĥľ
    0.06
    upal
    0.06
    è½®
    0.06
     Initi
    0.06
    URITY
    0.06
     Dou
    0.06
    Activations Density 0.000%

    No Known Activations