© 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. 15-LLAMASCOPE-RES-131K
    11. 86819
    Prev
    Next
    INDEX
    Explanations

    code snippets and expressions involving variable assignments and comparisons

    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
    iosper
    -0.07
    smith
    -0.07
    Ñģклад
    -0.07
    croft
    -0.07
    alus
    -0.07
    asal
    -0.07
    ahun
    -0.07
    bilt
    -0.07
    дÑĸл
    -0.07
    awai
    -0.07
    POSITIVE LOGITS
     Bened
    0.07
     current
    0.07
    tr
    0.06
    0.06
    oppins
    0.06
     tod
    0.06
     Jacobs
    0.05
     Accom
    0.05
     Current
    0.05
     CURRENT
    0.05
    Activations Density 0.087%

    No Known Activations