© 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 EvalsExportsAPI 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. 82900
    Prev
    Next
    INDEX
    Explanations

    significant numerical data, particularly ratings or scores related to items or experiences

    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
    vro
    -0.08
    ined
    -0.07
     Coff
    -0.07
    nel
    -0.06
     wil
    -0.06
    icies
    -0.06
    izzo
    -0.06
    azing
    -0.06
    ogy
    -0.06
    ook
    -0.06
    POSITIVE LOGITS
    cona
    0.07
    lashes
    0.07
    .scalablytyped
    0.06
     Baths
    0.06
    yun
    0.06
    RAINT
    0.06
    uw
    0.06
    èľ
    0.06
    Margins
    0.06
    °}
    0.06
    Activations Density 0.019%

    No Known Activations