© 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. 57243
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or 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
    ici
    -0.07
    ymb
    -0.07
    term
    -0.07
    encent
    -0.07
    crete
    -0.06
    runner
    -0.06
    poser
    -0.06
    _meter
    -0.06
    uber
    -0.06
    azine
    -0.06
    POSITIVE LOGITS
    chaft
    0.07
    liness
    0.07
    Stretch
    0.07
     Stretch
    0.07
    hu
    0.07
    islav
    0.07
    /stretch
    0.07
    ÙĪاج
    0.07
    ħ§
    0.06
    ãģªãģĮãĤī
    0.06
    Activations Density 0.031%

    No Known Activations