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

    Neuronpedia

    Jacobian LensNEW
    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. 59090
    Prev
    Next
    INDEX
    Explanations

    questions and prompts related to personal experiences and advice

    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
    sie
    -0.07
    self
    -0.06
     Intercept
    -0.06
    opic
    -0.06
    esco
    -0.06
    que
    -0.06
    NSUserDefaults
    -0.06
    ore
    -0.06
     llen
    -0.06
    eshire
    -0.06
    POSITIVE LOGITS
    kah
    0.07
    ormsg
    0.07
     Humph
    0.06
    .Names
    0.06
     lesson
    0.06
    _dbg
    0.06
    _parallel
    0.06
     advice
    0.06
    elho
    0.06
    {_
    0.06
    Activations Density 0.011%

    No Known Activations