© 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. 117510
    Prev
    Next
    INDEX
    Explanations

    citations and web links to sources

    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
    -valu
    -0.08
    ptide
    -0.07
    sar
    -0.07
     Ipsum
    -0.07
    ازÛĮ
    -0.06
    ibraries
    -0.06
    illet
    -0.06
    eria
    -0.06
    licted
    -0.06
    antom
    -0.06
    POSITIVE LOGITS
    алÑĸÑģÑĤ
    0.06
    Homepage
    0.06
    ipsis
    0.06
     mili
    0.06
     cro
    0.06
    298
    0.06
    ]âĢı
    0.06
    à¥ĩयर
    0.06
     OO
    0.05
     Tro
    0.05
    Activations Density 0.004%

    No Known Activations