© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27188
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate critical assessments or warnings about situations

    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
    kiye
    -0.07
    lessly
    -0.07
    eren
    -0.06
    >manual
    -0.06
    uko
    -0.06
    \↵
    -0.06
    -0.06
    oub
    -0.06
    elah
    -0.06
    ż
    -0.06
    POSITIVE LOGITS
    )
    0.08
     _______,
    0.07
    имÑĥ
    0.07
    лан
    0.06
     Wenger
    0.06
    Ĺı
    0.06
    !!,
    0.06
    AWN
    0.06
    (""),
    0.06
    íĬ
    0.06
    Activations Density 0.086%

    No Known Activations