© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 280
    Prev
    Next
    INDEX
    Explanations

    references to business opportunities and market strategies

    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
    .scalablytyped
    -0.08
     гÑĢо
    -0.07
    acionales
    -0.06
    pst
    -0.06
    omes
    -0.06
    Spoiler
    -0.06
    _ASSUME
    -0.06
    elop
    -0.06
     sic
    -0.06
    ndl
    -0.06
    POSITIVE LOGITS
     Cultural
    0.09
     Foreign
    0.07
     cultural
    0.07
     Lonely
    0.07
    ucks
    0.07
     Imported
    0.06
    -transparent
    0.06
     Resident
    0.06
    inese
    0.06
    æ¼¢
    0.06
    Activations Density 0.007%

    No Known Activations