© 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. 71217
    Prev
    Next
    INDEX
    Explanations

    welcoming phrases and references to games or software

    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
    engl
    -0.07
    ynos
    -0.07
    cone
    -0.07
    елÑĮно
    -0.06
    lder
    -0.06
    ongs
    -0.06
    uart
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    oit
    -0.06
    asn
    -0.06
    POSITIVE LOGITS
     RectTransform
    0.07
    456
    0.07
    -relative
    0.07
    filer
    0.07
    czy
    0.07
    ourd
    0.07
    uen
    0.07
    ãģ¡ãģ¯
    0.06
    ÅĽmy
    0.06
    408
    0.06
    Activations Density 0.004%

    No Known Activations