Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3490
    Prev
    Next
    INDEX
    Explanations

    instances of criticism or complaint in context

    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
    طار
    -0.07
    indow
    -0.07
    apiro
    -0.07
    .calls
    -0.07
     ÑģоÑģÑĤ
    -0.07
    æµİ
    -0.07
    침
    -0.07
    æ¿Ł
    -0.07
    漫
    -0.07
     Záp
    -0.07
    POSITIVE LOGITS
     off
    0.06
     privately
    0.06
    loy
    0.06
     his
    0.06
     vent
    0.06
     
    0.06
     family
    0.06
     ven
    0.05
     (
    0.05
    ,
    0.05
    Activations Density 0.075%

    No Known Activations