© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75568
    Prev
    Next
    INDEX
    Explanations

    terms related to professional roles and organizational structures

    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
     all
    -0.08
     sometimes
    -0.08
     and
    -0.07
     things
    -0.07
     each
    -0.07
     various
    -0.07
     everywhere
    -0.07
     a
    -0.07
     are
    -0.06
     often
    -0.06
    POSITIVE LOGITS
     nÃło
    0.13
     olursa
    0.10
     WHATSOEVER
    0.10
     кÑĢоме
    0.09
     Äįi
    0.09
    æĪĸ
    0.08
     или
    0.08
    gne
    0.08
     anywhere
    0.08
     whatsoever
    0.08
    Activations Density 0.129%

    No Known Activations