© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57482
    Prev
    Next
    INDEX
    Explanations

    negative responses or dismissive phrases

    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
    bew
    -0.09
    ëĿ¼ëıĦ
    -0.08
    egas
    -0.08
    \CMS
    -0.08
    intColor
    -0.08
    ÎŃÏģ
    -0.08
    práv
    -0.07
    лÑİб
    -0.07
    ãĥ«ãĥĪ
    -0.07
     sắc
    -0.07
    POSITIVE LOGITS
    ,
    0.08
     matter
    0.08
     wonder
    0.08
     no
    0.08
     surprise
    0.07
     No
    0.07
    pe
    0.07
     critically
    0.07
     need
    0.07
    ises
    0.07
    Activations Density 0.019%

    No Known Activations