© 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. 98790
    Prev
    Next
    INDEX
    Explanations

    HTML markup and structure

    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
    ibel
    -0.07
    boru
    -0.06
    echa
    -0.06
    alse
    -0.06
    rogate
    -0.06
     cust
    -0.06
    bt
    -0.06
    zim
    -0.06
    ey
    -0.06
    urg
    -0.06
    POSITIVE LOGITS
    wick
    0.08
    ãĥįãĥ«
    0.07
     Jou
    0.06
     ASSERT
    0.06
    nické
    0.06
    ADATA
    0.06
    离
    0.06
    ODY
    0.06
    355
    0.06
     rua
    0.06
    Activations Density 0.000%

    No Known Activations