© 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 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. 84345
    Prev
    Next
    INDEX
    Explanations

    numerical or coded references related to legislative or council sessions

    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
     Adv
    -0.06
    annel
    -0.06
    ditor
    -0.06
     g
    -0.06
     Zot
    -0.05
     Laboratory
    -0.05
     free
    -0.05
     Bayesian
    -0.05
     gr
    -0.05
    ÂŃ
    -0.05
    POSITIVE LOGITS
    apse
    0.07
    /assets
    0.07
    lluminate
    0.07
     konkrét
    0.07
     iddi
    0.07
    درس
    0.07
    OPSIS
    0.07
    (Expected
    0.07
     Incontri
    0.07
    oston
    0.06
    Activations Density 0.002%

    No Known Activations