© 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. 22-LLAMASCOPE-RES-131K
    11. 4202
    Prev
    Next
    INDEX
    Explanations

    key phrases and words related to evaluation and change

    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
    .scalablytyped
    -0.07
    esk
    -0.07
     à¤ĩसल
    -0.07
     porque
    -0.07
     because
    -0.06
    essional
    -0.06
    because
    -0.06
     parce
    -0.06
    uars
    -0.06
    ãģłãģĭãĤī
    -0.06
    POSITIVE LOGITS
     apparently
    0.08
    ibold
    0.08
    vre
    0.07
     denn
    0.07
     καθÏİÏĤ
    0.07
     إذ
    0.07
    tee
    0.07
    425
    0.07
    mma
    0.07
    ãģĭãģ®
    0.07
    Activations Density 0.056%

    No Known Activations