© 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. 4753
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or refusal in a context

    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
    abel
    -0.07
    otel
    -0.06
    Ñģли
    -0.06
    ynchronized
    -0.06
    247
    -0.06
    sted
    -0.06
    ogan
    -0.06
    constant
    -0.06
     Sommer
    -0.06
    Await
    -0.06
    POSITIVE LOGITS
     future
    0.18
     forever
    0.17
    future
    0.16
     Future
    0.13
    Future
    0.12
    .future
    0.12
     Forever
    0.12
     ever
    0.12
     anymore
    0.11
    æ°¸
    0.11
    Activations Density 0.053%

    No Known Activations