© 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. 9-LLAMASCOPE-RES-131K
    11. 98517
    Prev
    Next
    INDEX
    Explanations

    references to companies and their activities

    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
    ÙĦاÙĦ
    -0.07
    ventus
    -0.07
    UMP
    -0.07
    wnd
    -0.06
    ukt
    -0.06
    ronic
    -0.06
    PLAN
    -0.06
    ktop
    -0.06
    wik
    -0.06
    rido
    -0.06
    POSITIVE LOGITS
     sublic
    0.06
    cock
    0.06
    ka
    0.06
     lift
    0.06
    ully
    0.06
    åł´
    0.06
     nguyá»ĩn
    0.06
    /kubernetes
    0.06
     RAT
    0.06
    اطر
    0.06
    Activations Density 0.002%

    No Known Activations