© 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. 54480
    Prev
    Next
    INDEX
    Explanations

    references to critical assessment and structural analysis

    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
    ness
    -0.07
    âĢ¦
    -0.07
     âĢ¦
    -0.07
     âĢ¦↵
    -0.06
     ..↵
    -0.06
    âĢ¦↵
    -0.06
    otta
    -0.06
    /topics
    -0.06
    âĢ¦the
    -0.05
     ..
    -0.05
    POSITIVE LOGITS
     -*-č↵
    0.10
     skoro
    0.08
    Äįel
    0.07
    arkan
    0.07
    JNI
    0.07
    -addons
    0.07
    à¹Ĩ
    0.07
    ASIC
    0.07
     Ùħباش
    0.07
    ëł
    0.07
    Activations Density 0.050%

    No Known Activations