© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    instances of editorial commentary and changes to articles

    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
    wal
    -0.07
    mand
    -0.06
    akh
    -0.06
    alı
    -0.06
    MAND
    -0.05
    ough
    -0.05
     seem
    -0.05
    585
    -0.05
     BaseEntity
    -0.05
    ewed
    -0.05
    POSITIVE LOGITS
    orrect
    0.09
     correct
    0.09
    Å¡ov
    0.08
     Correct
    0.08
     indeb
    0.08
    vider
    0.07
    ibu
    0.07
     Proper
    0.07
     eskort
    0.07
     pán
    0.07
    Activations Density 0.005%

    No Known Activations