© 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. 105012
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce contrasting or opposing ideas

    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
    orra
    -0.08
    orian
    -0.08
    ÑĤÑĢон
    -0.07
    ledger
    -0.07
    heimer
    -0.07
    ÑģÑĤÑĢе
    -0.07
    æ½
    -0.07
    èĶ
    -0.07
     íıī
    -0.06
    mî
    -0.06
    POSITIVE LOGITS
     apparently
    0.08
     somehow
    0.06
     instead
    0.06
    Apparently
    0.06
     inconvenient
    0.06
     Apparently
    0.06
     Wein
    0.06
    idi
    0.06
     conveniently
    0.06
    ensem
    0.06
    Activations Density 0.054%

    No Known Activations