© 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. 95229
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize the importance or significance of something through repetition

    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
    Also
    -0.09
    idon
    -0.08
    ä¹Łä¸į
    -0.08
    also
    -0.08
    ptions
    -0.07
    ÑĥÑĤи
    -0.07
    aden
    -0.07
     ÑĤакже
    -0.07
    ÙĪدÙĩ
    -0.07
     Also
    -0.07
    POSITIVE LOGITS
     called
    0.07
     consists
    0.07
    alis
    0.06
     consist
    0.06
     consisted
    0.06
    858
    0.06
    972
    0.06
    ent
    0.06
    369
    0.06
    Called
    0.06
    Activations Density 0.042%

    No Known Activations