© 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. 103879
    Prev
    Next
    INDEX
    Explanations

    references to specific formats, quantities, and measurements related to various subjects

    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
    aviour
    -0.07
    utterstock
    -0.07
    éľĬ
    -0.07
    IGHL
    -0.07
    ground
    -0.07
     INLINE
    -0.07
    eba
    -0.07
    MainThread
    -0.07
    odzi
    -0.07
    chair
    -0.07
    POSITIVE LOGITS
     ones
    0.08
     most
    0.06
    ual
    0.06
    499
    0.06
    iren
    0.06
     or
    0.05
     Ones
    0.05
     residential
    0.05
    appa
    0.05
     contempor
    0.05
    Activations Density 0.025%

    No Known Activations