© 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. 30253
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts, compounds, and their classifications

    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
     Rescue
    -0.07
     yeast
    -0.06
     rescue
    -0.06
     Sadd
    -0.06
    essian
    -0.06
    rvine
    -0.06
    vent
    -0.06
    £
    -0.06
     Relief
    -0.06
    æ°§
    -0.06
    POSITIVE LOGITS
    ogui
    0.08
    kova
    0.07
     Armed
    0.07
    ibold
    0.07
    ]={↵
    0.07
    estro
    0.07
    .AF
    0.07
    .GraphicsUnit
    0.07
    ")!=
    0.07
    igue
    0.06
    Activations Density 0.001%

    No Known Activations