© 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. 90262
    Prev
    Next
    INDEX
    Explanations

    references to academic articles and discussions within a structured format

    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
    ën
    -0.07
    allen
    -0.07
    aram
    -0.06
    igt
    -0.06
    ixer
    -0.06
    ipers
    -0.06
    umont
    -0.06
     feudal
    -0.05
    awai
    -0.05
     sing
    -0.05
    POSITIVE LOGITS
    é¼»
    0.07
    _nth
    0.07
    .scalablytyped
    0.07
    mite
    0.07
    ANTLR
    0.07
    θο
    0.07
    Nonce
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    _Details
    0.06
    teki
    0.06
    Activations Density 0.017%

    No Known Activations