© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    key statistics and performance metrics in sports

    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
     uk
    -0.08
    achu
    -0.07
    .MixedReality
    -0.07
    resses
    -0.07
    Å©i
    -0.07
    rahim
    -0.07
    å·
    -0.07
    ekil
    -0.07
    readcr
    -0.07
     British
    -0.06
    POSITIVE LOGITS
    asl
    0.08
    anda
    0.07
     Ras
    0.06
     몰
    0.06
    ĵį
    0.06
     Shed
    0.06
    ÑĤоÑĩ
    0.06
    มห
    0.06
     torment
    0.06
    ewis
    0.06
    Activations Density 0.000%

    No Known Activations