© 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. 17-LLAMASCOPE-RES-131K
    11. 75470
    Prev
    Next
    INDEX
    Explanations

    references to replacements or substitutions for items or components

    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
    aba
    -0.07
     Tow
    -0.07
    Ñģклад
    -0.07
    ittest
    -0.07
     Ages
    -0.07
     awakeFromNib
    -0.06
    place
    -0.06
    ingham
    -0.06
    /py
    -0.06
    帽
    -0.06
    POSITIVE LOGITS
    /add
    0.08
    /update
    0.08
    parts
    0.07
     Parts
    0.07
    /helper
    0.07
    /mock
    0.07
    ãĤ¥
    0.07
    375
    0.07
     parts
    0.07
    675
    0.07
    Activations Density 0.007%

    No Known Activations