© 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. 124232
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and nostalgia

    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
    zych
    -0.07
    aña
    -0.07
     experiment
    -0.06
     beginning
    -0.06
    roadcast
    -0.06
    Äħż
    -0.06
    ecast
    -0.06
    aaS
    -0.06
    à¥įà¤
    -0.06
     Dy
    -0.06
    POSITIVE LOGITS
    orney
    0.07
    ayscale
    0.07
    bÃŃ
    0.07
    luk
    0.06
    견
    0.06
    blas
    0.06
     cầm
    0.06
     ëĭ¹ìĭľ
    0.06
     Cousins
    0.06
    åħ¼
    0.06
    Activations Density 0.001%

    No Known Activations