© 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. 75725
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainties in the text

    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
    esson
    -0.08
    çĢ¬
    -0.07
    /console
    -0.07
    æĹħè¡Į
    -0.06
    .scalablytyped
    -0.06
    ãĥ«ãĥķ
    -0.06
    verity
    -0.06
    /Graphics
    -0.06
    unny
    -0.06
    éŁ³æ¥½
    -0.06
    POSITIVE LOGITS
     alternative
    0.10
     other
    0.10
     alternate
    0.09
    alternative
    0.09
     alternatives
    0.09
    åħ¶ä»ĸ
    0.08
    Alternative
    0.08
    other
    0.08
     altri
    0.08
     better
    0.08
    Activations Density 0.007%

    No Known Activations