© 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. 17922
    Prev
    Next
    INDEX
    Explanations

    references to the name "Eddie" and its variations or related forms in the text

    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
    sk
    -0.07
    ncia
    -0.07
    ãģĴ
    -0.07
    nen
    -0.07
    aida
    -0.07
    opy
    -0.07
    neas
    -0.07
    mes
    -0.07
    nÃŃ
    -0.07
    anks
    -0.07
    POSITIVE LOGITS
    elf
    0.07
    ied
    0.06
    Utf
    0.06
     Gut
    0.06
     Relax
    0.06
    fy
    0.06
    unset
    0.06
     uncomment
    0.05
     اÙĦاÙĨت
    0.05
     relax
    0.05
    Activations Density 0.003%

    No Known Activations