© 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. 129104
    Prev
    Next
    INDEX
    Explanations

    positive descriptors or adjectives that express quality

    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
    olle
    -0.06
    oldemort
    -0.06
    ients
    -0.06
    eyim
    -0.06
    ndx
    -0.06
    _encoded
    -0.06
    ugo
    -0.06
    eton
    -0.06
    QT
    -0.06
    ãĤ¦ãĥ³
    -0.06
    POSITIVE LOGITS
     way
    0.10
     ways
    0.09
    .way
    0.08
    weise
    0.07
     addition
    0.07
    arend
    0.07
    agn
    0.07
    /Resources
    0.06
     example
    0.06
     starting
    0.06
    Activations Density 0.020%

    No Known Activations