© 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 EvalsExportsAPI 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. 71311
    Prev
    Next
    INDEX
    Explanations

    phrases indicating action-packed or thrilling content in media reviews

    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
    ieber
    -0.07
     Circ
    -0.06
    çķ°
    -0.06
    Prefs
    -0.06
    _RET
    -0.06
    essages
    -0.06
    =yes
    -0.06
    dda
    -0.06
    mia
    -0.06
    祥
    -0.06
    POSITIVE LOGITS
     episode
    0.11
     weekly
    0.10
     Episode
    0.09
    Weekly
    0.09
     Weekly
    0.09
    weekly
    0.08
    episode
    0.08
    Episode
    0.08
     week
    0.07
    riday
    0.06
    Activations Density 0.054%

    No Known Activations