© 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. 129683
    Prev
    Next
    INDEX
    Explanations

    frequent use of the word "About" in various contexts

    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
    äºĭåĭĻ
    -0.07
    缼
    -0.07
     Hud
    -0.07
    миÑĤ
    -0.07
    Cb
    -0.07
    виг
    -0.07
    mbH
    -0.07
    erce
    -0.06
    enz
    -0.06
    ingle
    -0.06
    POSITIVE LOGITS
    535
    0.06
    ãĥ³ãĥĩ
    0.06
     about
    0.06
    elry
    0.06
    oj
    0.06
     Dixon
    0.06
    ughter
    0.06
    idis
    0.06
    ÑĢоб
    0.06
    edl
    0.06
    Activations Density 0.004%

    No Known Activations