© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124764
    Prev
    Next
    INDEX
    Explanations

    references to government policies and proposals

    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
     нал
    -0.07
    gross
    -0.07
     FileAccess
    -0.07
     parach
    -0.07
    adal
    -0.07
    .gdx
    -0.07
    .crm
    -0.06
    ìĬ¤íĭ°
    -0.06
     пок
    -0.06
    íĮIJ
    -0.06
    POSITIVE LOGITS
     Immigration
    0.06
    acie
    0.06
     immigration
    0.06
    guard
    0.06
     guard
    0.06
    670
    0.06
     immigrants
    0.05
     concert
    0.05
    UTDOWN
    0.05
     Alexandra
    0.05
    Activations Density 0.004%

    No Known Activations