© 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. 104203
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inability or incompetence

    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
    akan
    -0.08
    amax
    -0.07
     Roc
    -0.07
    Interop
    -0.07
    WAY
    -0.06
    ÏĢή
    -0.06
    aggi
    -0.06
    że
    -0.06
    Mutable
    -0.06
    zn
    -0.06
    POSITIVE LOGITS
    simple
    0.08
     simplest
    0.07
     simple
    0.07
     Commit
    0.07
     basic
    0.06
     EITHER
    0.06
    proper
    0.06
    commit
    0.06
    _basic
    0.06
    æŃ£å¸¸
    0.06
    Activations Density 0.037%

    No Known Activations