© 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. 70522
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate problem-solving or figuring things out

    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
    ält
    -0.07
    aylight
    -0.07
    ne
    -0.07
    θε
    -0.07
    askan
    -0.07
    ulfilled
    -0.07
    antro
    -0.07
    .Compare
    -0.07
    QT
    -0.06
    rière
    -0.06
    POSITIVE LOGITS
     how
    0.08
     ways
    0.07
     puzzles
    0.06
    éĴ®
    0.06
    iá»ģn
    0.06
     whether
    0.06
     why
    0.06
     Knot
    0.06
    aya
    0.06
    å¦Ĥä½ķ
    0.06
    Activations Density 0.007%

    No Known Activations