© 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. 93912
    Prev
    Next
    INDEX
    Explanations

    references to various organizations and advocacy groups

    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
    izik
    -0.07
    оби
    -0.07
    ace
    -0.06
    eldon
    -0.06
    reffen
    -0.06
     personally
    -0.06
    [at
    -0.06
    apphire
    -0.06
    eln
    -0.06
    ilk
    -0.06
    POSITIVE LOGITS
     such
    0.11
    such
    0.08
     organizations
    0.08
    /groups
    0.07
     organisations
    0.07
     SUCH
    0.07
     aliqua
    0.07
     groups
    0.07
    organizations
    0.07
     Watts
    0.07
    Activations Density 0.036%

    No Known Activations