© 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. 125867
    Prev
    Next
    INDEX
    Explanations

    Python programming constructs, specifically function and class definitions

    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
    ixon
    -0.07
    itals
    -0.06
     retreat
    -0.06
     à¹Ģส
    -0.06
    708
    -0.06
     Ultr
    -0.05
    normally
    -0.05
    mass
    -0.05
    xbd
    -0.05
    backward
    -0.05
    POSITIVE LOGITS
    SSIP
    0.08
    azio
    0.08
    alist
    0.07
    wart
    0.07
    æŀĿ
    0.07
    quin
    0.07
    eec
    0.06
    wat
    0.06
    ilage
    0.06
    pytest
    0.06
    Activations Density 0.007%

    No Known Activations