© 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. 92536
    Prev
    Next
    INDEX
    Explanations

    mentions of sharing personal experiences and visual content

    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
    ä¸Ģ度
    -0.07
     rival
    -0.06
    author
    -0.06
     Edition
    -0.06
    ź
    -0.06
    -CP
    -0.06
     Fro
    -0.06
    ovi
    -0.06
    land
    -0.05
    缸æīĭ
    -0.05
    POSITIVE LOGITS
     recent
    0.09
    _recent
    0.08
    recent
    0.07
    æĪij
    0.07
    andom
    0.07
     my
    0.07
     beaut
    0.07
    iyim
    0.07
    some
    0.07
    aris
    0.07
    Activations Density 0.023%

    No Known Activations