© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 103904
    Prev
    Next
    INDEX
    Explanations

    positive outcomes or triumphs

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ernote
    -0.07
    apis
    -0.07
    ulp
    -0.07
    æį·
    -0.07
    FAST
    -0.07
    Ä°Z
    -0.07
    UGC
    -0.07
    ipt
    -0.07
    ivre
    -0.07
    ì¹ĺ
    -0.07
    POSITIVE LOGITS
    0.07
    iggers
    0.06
    Liter
    0.06
    lol
    0.06
     seper
    0.06
    igger
    0.06
    itta
    0.06
    202
    0.06
     fucking
    0.06
     statewide
    0.06
    Activations Density 0.000%

    No Known Activations