© 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. 72600
    Prev
    Next
    INDEX
    Explanations

    phrases that express urgency or stress the importance of timing and preparedness

    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
     Minds
    -0.07
     Antworten
    -0.06
    rame
    -0.06
    ema
    -0.06
    itch
    -0.06
    _TRY
    -0.06
     æĺ
    -0.06
    veral
    -0.06
    ragen
    -0.06
     Heard
    -0.06
    POSITIVE LOGITS
    aney
    0.07
    strup
    0.07
     enough
    0.07
    vanished
    0.07
     sufficiently
    0.07
    agus
    0.07
    inha
    0.07
    ethylene
    0.07
    insky
    0.06
     mktime
    0.06
    Activations Density 0.023%

    No Known Activations