© 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. 119415
    Prev
    Next
    INDEX
    Explanations

    themes and metrics related to data analysis and statistics

    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
     Güven
    -0.08
    ŀĭ
    -0.07
    èĤ
    -0.06
    /--
    -0.06
    нож
    -0.06
    =YES
    -0.06
    mour
    -0.06
    ttp
    -0.06
    êu
    -0.06
    hausen
    -0.06
    POSITIVE LOGITS
     table
    0.09
     breakdown
    0.08
    åıĬ
    0.07
     comparison
    0.07
     chart
    0.07
     analysis
    0.07
     Table
    0.07
    omers
    0.06
    åıĬåħ¶
    0.06
     history
    0.06
    Activations Density 0.055%

    No Known Activations