© 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. 9-LLAMASCOPE-RES-131K
    11. 96418
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, duration, or distance

    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
    bjerg
    -0.07
    registers
    -0.07
    istring
    -0.07
    iros
    -0.07
    ÅŁa
    -0.07
    STALL
    -0.07
    HTTPHeader
    -0.07
    dae
    -0.06
    INET
    -0.06
    ãģ£ãģ±
    -0.06
    POSITIVE LOGITS
    agon
    0.07
    143
    0.06
    ritic
    0.06
    ardy
    0.06
    è®
    0.06
    allery
    0.06
    656
    0.06
    NL
    0.06
    383
    0.06
     distant
    0.05
    Activations Density 0.121%

    No Known Activations