© 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. 126390
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or health conditions

    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
    nger
    -0.07
    ault
    -0.07
    BUG
    -0.07
    è¶Ĭ
    -0.06
    aken
    -0.06
    ckpt
    -0.06
     Sullivan
    -0.06
     teb
    -0.06
    blink
    -0.06
    urar
    -0.06
    POSITIVE LOGITS
     Dün
    0.06
     a
    0.06
    ienda
    0.06
    'gc
    0.06
     Organic
    0.06
     Fol
    0.06
     Mein
    0.06
     Scre
    0.06
    istrovstvÃŃ
    0.06
    eydi
    0.06
    Activations Density 0.018%

    No Known Activations