© 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. 38770
    Prev
    Next
    INDEX
    Explanations

    references to leadership and accomplishments

    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
    åľŃ
    -0.07
     vá»ijn
    -0.06
    tees
    -0.06
    ÑĤеÑģÑĮ
    -0.06
    ubbo
    -0.06
    .aspx
    -0.06
     fu
    -0.06
    ãĥ³ãĥ
    -0.06
     fier
    -0.06
    ãģĮãģĬ
    -0.06
    POSITIVE LOGITS
     effort
    0.10
     efforts
    0.09
     handling
    0.08
    ourn
    0.08
     turnout
    0.08
     guts
    0.08
     achievements
    0.07
     overall
    0.07
     contribution
    0.07
     handled
    0.07
    Activations Density 0.055%

    No Known Activations