© 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. 78201
    Prev
    Next
    INDEX
    Explanations

    discussions around community involvement and shared accomplishments

    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
     itself
    -0.13
     himself
    -0.10
     Ñıке
    -0.09
    æĺ¯ä¸ª
    -0.08
     à¤īसन
    -0.08
     sám
    -0.08
     its
    -0.08
     à¤īसà¤ķ
    -0.08
     Ø®ÙĪدش
    -0.08
    æĺ¯ä¸Ģ个
    -0.07
    POSITIVE LOGITS
     themselves
    0.39
     their
    0.23
    Their
    0.22
     Their
    0.21
    their
    0.21
     thems
    0.19
     leurs
    0.18
     иÑħ
    0.15
     jejich
    0.15
     leur
    0.15
    Activations Density 0.737%

    No Known Activations