© 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. 62202
    Prev
    Next
    INDEX
    Explanations

    details related to event organization and logistics

    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
     PartialView
    -0.08
    客
    -0.08
    âĹİ
    -0.07
    eson
    -0.07
    antro
    -0.07
    abis
    -0.07
    Appe
    -0.07
    _INLINE
    -0.07
    zbek
    -0.07
    cek
    -0.07
    POSITIVE LOGITS
    bat
    0.07
     staffers
    0.06
     Breakfast
    0.06
     rou
    0.06
    evil
    0.06
     breakfast
    0.06
     test
    0.06
     ÑĤеÑģÑĤ
    0.06
    Allocator
    0.06
    OU
    0.06
    Activations Density 0.012%

    No Known Activations