© 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. 17-LLAMASCOPE-RES-131K
    11. 126210
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles

    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
     Dit
    -0.07
    800
    -0.06
    Å¡tÄĽnÃŃ
    -0.06
     Kraj
    -0.06
    imi
    -0.06
    ilim
    -0.06
    oretical
    -0.06
     Lazar
    -0.06
    okino
    -0.06
    ntity
    -0.05
    POSITIVE LOGITS
    æ°ı
    0.08
     himself
    0.08
     Himself
    0.07
    erli
    0.07
    izr
    0.07
    æ´¥
    0.07
    eph
    0.06
     Mun
    0.06
    Forgery
    0.06
    .gb
    0.06
    Activations Density 0.021%

    No Known Activations