© 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. 61889
    Prev
    Next
    INDEX
    Explanations

    elements related to structured programs and their processes

    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
     your
    -0.07
    izi
    -0.06
    iva
    -0.06
    aket
    -0.06
     will
    -0.06
     please
    -0.06
    lesi
    -0.06
    owler
    -0.06
    angu
    -0.06
     shall
    -0.06
    POSITIVE LOGITS
     रहत
    0.08
    ãĥ¼ãĥ©
    0.07
    خاÙĨ
    0.07
    tesy
    0.07
    clr
    0.07
    icho
    0.07
     bý
    0.07
    ÃĹ↵↵
    0.07
    .rmi
    0.07
    Gratis
    0.07
    Activations Density 0.008%

    No Known Activations