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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89773
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their communication details

    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
    chop
    -0.07
    chine
    -0.07
    .Writer
    -0.07
    laughter
    -0.07
    chte
    -0.07
    æĭ³
    -0.06
     nop
    -0.06
    повÑĸд
    -0.06
    advertisement
    -0.06
     banc
    -0.06
    POSITIVE LOGITS
    å¤ĩ注
    0.07
     manually
    0.06
     contact
    0.06
    SetActive
    0.06
     Rol
    0.06
     Sanford
    0.06
    contact
    0.06
     clients
    0.06
    manuel
    0.06
    üzel
    0.06
    Activations Density 0.004%

    No Known Activations