© 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. 106276
    Prev
    Next
    INDEX
    Explanations

    statements that emphasize or highlight specific facts

    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
     Neutral
    -0.06
    ix
    -0.06
    179
    -0.06
    stral
    -0.06
    :↵
    -0.06
    elda
    -0.06
     XmlNode
    -0.06
    arian
    -0.06
    sh
    -0.05
     mall
    -0.05
    POSITIVE LOGITS
     fact
    0.13
     fakt
    0.08
     facts
    0.08
     FACT
    0.08
    Fact
    0.08
    fact
    0.08
    FACT
    0.08
     ÑĦак
    0.07
     Fact
    0.07
    _fact
    0.07
    Activations Density 0.005%

    No Known Activations