© 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 EvalsExportsinterp-engineNEWAPI 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. 73450
    Prev
    Next
    INDEX
    Explanations

    content-related words and phrases indicating promotion or provocation

    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
    idot
    -0.07
    earch
    -0.07
    uri
    -0.07
    NullOrEmpty
    -0.07
    458
    -0.06
    601
    -0.06
    457
    -0.06
    beiten
    -0.06
    uchs
    -0.06
    ÑĤÑĢон
    -0.06
    POSITIVE LOGITS
    gers
    0.08
    ess
    0.07
    insi
    0.07
    åħ
    0.07
    aine
    0.07
    ost
    0.07
    lox
    0.07
    rag
    0.06
     Rac
    0.06
    374
    0.06
    Activations Density 0.006%

    No Known Activations