© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93370
    Prev
    Next
    INDEX
    Explanations

    references to formal proposals or submissions related to rights and reforms

    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
     Dirt
    -0.07
     dirt
    -0.06
     Buen
    -0.06
    enas
    -0.06
    审
    -0.06
    Caller
    -0.06
    무
    -0.06
    à¸Ľà¸£à¸°à¸ģาศ
    -0.06
    ki
    -0.05
    getSource
    -0.05
    POSITIVE LOGITS
     submission
    0.10
     submitted
    0.09
     submissions
    0.09
     contribution
    0.09
     inputs
    0.09
    submit
    0.09
    rieve
    0.08
     Submission
    0.08
     input
    0.08
     submit
    0.08
    Activations Density 0.013%

    No Known Activations