© 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. 17-LLAMASCOPE-RES-131K
    11. 78415
    Prev
    Next
    INDEX
    Explanations

    high-frequency conjunctions and articles

    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
    maz
    -0.07
     вÑģего
    -0.06
    urma
    -0.06
    akov
    -0.06
    enet
    -0.06
    ertil
    -0.06
     scar
    -0.06
     enjoy
    -0.06
    arc
    -0.06
     jestli
    -0.06
    POSITIVE LOGITS
    hlen
    0.08
    inality
    0.07
     ï½ľ
    0.07
    оÑģÑĢед
    0.07
    744
    0.07
    æĪijçļĦ
    0.06
    ülen
    0.06
    iento
    0.06
    inal
    0.06
    íĥģ
    0.06
    Activations Density 0.000%

    No Known Activations