© 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. 103612
    Prev
    Next
    INDEX
    Explanations

    references to contests or challenges related to creative projects

    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
     Canton
    -0.06
     Liberties
    -0.06
    GenerationStrategy
    -0.06
     Jury
    -0.06
    MemoryWarning
    -0.06
     recorded
    -0.05
    eyen
    -0.05
     tieten
    -0.05
     Mercy
    -0.05
    CloseOperation
    -0.05
    POSITIVE LOGITS
     challenge
    0.09
    仪
    0.08
    ÑĢави
    0.07
     community
    0.07
    جاÙħ
    0.07
    obl
    0.07
    challenge
    0.07
    community
    0.07
    .community
    0.07
    ember
    0.07
    Activations Density 0.044%

    No Known Activations