© 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. 72204
    Prev
    Next
    INDEX
    Explanations

    references to gatherings or groups of people

    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
     å¾Ĵ
    -0.07
    ойно
    -0.07
    ênh
    -0.07
    елиÑĩ
    -0.07
    emoc
    -0.07
    над
    -0.07
    rsa
    -0.06
    éŃĤ
    -0.06
    URLConnection
    -0.06
    umper
    -0.06
    POSITIVE LOGITS
    abouts
    0.07
    335
    0.07
    357
    0.07
    punkt
    0.06
    agna
    0.06
    /on
    0.06
    355
    0.06
     Anders
    0.06
    iphery
    0.06
    pace
    0.06
    Activations Density 0.022%

    No Known Activations