© 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. 15-LLAMASCOPE-RES-131K
    11. 103821
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or demographics related to populations

    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
    ÑĢ
    -0.07
     Tits
    -0.06
    uela
    -0.06
    ombat
    -0.06
     serv
    -0.06
    zar
    -0.06
    loquent
    -0.05
    olin
    -0.05
     Ekon
    -0.05
    íĴĪ
    -0.05
    POSITIVE LOGITS
    ourg
    0.08
    entin
    0.07
    ownik
    0.07
     neither
    0.07
     representation
    0.06
     representations
    0.06
    æł¹
    0.06
     Quarter
    0.06
    plex
    0.06
    ä¸įåĪ°
    0.06
    Activations Density 0.008%

    No Known Activations