© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical terminology

    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
    ayas
    -0.06
    noinspection
    -0.06
    chet
    -0.06
    à¸ļาล
    -0.06
     جÛĮ
    -0.06
    uuml
    -0.06
     '''
    -0.06
     bols
    -0.06
    ayment
    -0.06
    опÑĢоÑģ
    -0.06
    POSITIVE LOGITS
    ukt
    0.06
    ilo
    0.06
    dater
    0.06
    kul
    0.06
    ave
    0.05
    ig
    0.05
    ala
    0.05
    pend
    0.05
     prest
    0.05
    kte
    0.05
    Activations Density 0.074%

    No Known Activations