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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84804
    Prev
    Next
    INDEX
    Explanations

    references to time and the state of existing methods or technologies

    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
    ɵ
    -0.07
     recently
    -0.07
     lately
    -0.06
     previously
    -0.06
    recent
    -0.06
     recent
    -0.06
    aji
    -0.06
    olla
    -0.06
     originally
    -0.06
    179
    -0.06
    POSITIVE LOGITS
     standards
    0.08
    ạc
    0.07
    ิว
    0.07
     kå
    0.07
    -standard
    0.07
     efforts
    0.07
    practice
    0.07
    ucher
    0.07
    ALER
    0.06
    -available
    0.06
    Activations Density 0.016%

    No Known Activations