© 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. 126246
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and specific brands or products

    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
     yyn
    -0.07
    uiltin
    -0.07
     zdrav
    -0.07
    afone
    -0.06
     Dess
    -0.06
     —↵↵
    -0.06
    imbus
    -0.06
    bidden
    -0.06
     ÑĢанÑĮ
    -0.06
    à¥ĭà¤Ĥ,
    -0.06
    POSITIVE LOGITS
    æ°ı
    0.07
    ÅĦst
    0.07
    åĪĩ
    0.07
    jÄħ
    0.06
    ÃĥO
    0.06
    åĢij
    0.06
    ownik
    0.06
    anda
    0.06
    SingleOrDefault
    0.06
    SION
    0.06
    Activations Density 0.012%

    No Known Activations