© 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. 95382
    Prev
    Next
    INDEX
    Explanations

    key terms related to importance and significance

    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
     reasonably
    -0.07
     Locker
    -0.06
    ogle
    -0.06
    ehler
    -0.06
    aze
    -0.06
    alon
    -0.06
    antu
    -0.06
    ivate
    -0.05
     Goldman
    -0.05
    ospace
    -0.05
    POSITIVE LOGITS
    ãĥ¶
    0.07
    ãĥ¡ãĥ©
    0.07
    .Players
    0.07
    ãĥ©ãĤ¤ãĥ³
    0.07
    PLOY
    0.07
    Injected
    0.07
    .tbl
    0.07
     showc
    0.07
    æĮĻ
    0.07
    ãĥ¼ãĥģ
    0.07
    Activations Density 0.001%

    No Known Activations