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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 42258
    Prev
    Next
    INDEX
    Explanations

    predictions and assessments related to probability and likelihood

    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
    à¸Ńาà¸Ī
    -0.08
     supposedly
    -0.07
     sometimes
    -0.07
     hopefully
    -0.07
     allegedly
    -0.07
     potentially
    -0.07
    оÑģÑĮ
    -0.07
     sanki
    -0.07
    oret
    -0.07
     Sometimes
    -0.07
    POSITIVE LOGITS
     soon
    0.08
     next
    0.08
     eventually
    0.07
    ewise
    0.07
     sooner
    0.07
     пÑĢидеÑĤÑģÑı
    0.07
    hood
    0.07
     eventual
    0.07
     Eventually
    0.07
    ãģķãĤī
    0.06
    Activations Density 0.036%

    No Known Activations