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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40748
    Prev
    Next
    INDEX
    Explanations

    expressions related to the concepts of "something" and "nothing."

    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
    fw
    -0.07
    EIF
    -0.06
    istrate
    -0.06
    ette
    -0.05
    mo
    -0.05
     tact
    -0.05
    arro
    -0.05
    åĿĬ
    -0.05
    æľī
    -0.05
    asion
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.07
    à¹Ģลย
    0.07
    burger
    0.07
    zdy
    0.07
     done
    0.07
    ullan
    0.07
    bjerg
    0.07
    اÛĮØ´
    0.07
     Done
    0.07
     øns
    0.07
    Activations Density 0.013%

    No Known Activations