© 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. 17705
    Prev
    Next
    INDEX
    Explanations

    formal reports and detailed descriptions of projects or studies

    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
    ople
    -0.07
    aml
    -0.07
     latest
    -0.06
     aktu
    -0.06
    اÙĬد
    -0.06
     newest
    -0.06
    opor
    -0.06
     Marvin
    -0.06
    abyrin
    -0.06
    è¶Ĭ
    -0.06
    POSITIVE LOGITS
    -era
    0.08
    cheng
    0.07
     cellForRowAt
    0.07
    zung
    0.07
     era
    0.07
    already
    0.07
    ohan
    0.07
     already
    0.07
    以æĿ¥
    0.07
     iken
    0.07
    Activations Density 0.038%

    No Known Activations