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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127856
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and expressions of doubt about performance

    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
    oux
    -0.08
    407
    -0.07
    DataSource
    -0.07
    ales
    -0.07
    ÏĢά
    -0.07
     suspended
    -0.06
     klar
    -0.06
    osit
    -0.06
    ë¯
    -0.06
    utherford
    -0.06
    POSITIVE LOGITS
     Linear
    0.06
    urity
    0.06
     undue
    0.06
    γÏī
    0.06
    ered
    0.06
    Ñĭл
    0.06
    byss
    0.06
    quota
    0.06
     uncont
    0.06
    emo
    0.06
    Activations Density 0.022%

    No Known Activations