© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126464
    Prev
    Next
    INDEX
    Explanations

    references to academic qualifications and degrees in administration

    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
    Ìĥ
    -0.08
    udeau
    -0.07
     Specialists
    -0.07
     bilim
    -0.07
    endor
    -0.07
    antal
    -0.07
    átor
    -0.07
    ÌĪ
    -0.07
    /dist
    -0.07
    ennie
    -0.07
    POSITIVE LOGITS
     Whitney
    0.06
    hift
    0.06
    ÃĴ
    0.06
     Laf
    0.06
    trand
    0.06
    ÛĮاÙĨ
    0.06
    326
    0.06
    cox
    0.06
    .Axis
    0.06
     Sloan
    0.05
    Activations Density 0.002%

    No Known Activations