© 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. 16679
    Prev
    Next
    INDEX
    Explanations

    mentions of colors and other visual elements in various contexts

    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
    illes
    -0.07
     Fach
    -0.06
     Nach
    -0.06
     Nab
    -0.06
     elsewhere
    -0.05
    anja
    -0.05
     alone
    -0.05
     pred
    -0.05
    ely
    -0.05
     any
    -0.05
    POSITIVE LOGITS
     birden
    0.10
     equally
    0.08
     ÑĢазом
    0.08
     Äijá»ģu
    0.08
    /all
    0.08
    ä¸Ģ度
    0.08
    except
    0.07
    ãģ§ãģ¯ãģªãģı
    0.07
    ommen
    0.07
    LocalizedMessage
    0.07
    Activations Density 0.055%

    No Known Activations