© 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 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. 78407
    Prev
    Next
    INDEX
    Explanations

    references to time and duration related to involvement or participation in activities

    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
    gid
    -0.07
    ascus
    -0.07
    nova
    -0.06
    fx
    -0.06
    Certain
    -0.06
    atism
    -0.06
    aliz
    -0.06
    ¤í
    -0.06
    abin
    -0.06
     Electronic
    -0.06
    POSITIVE LOGITS
     inception
    0.10
     earliest
    0.09
    early
    0.09
     early
    0.08
     original
    0.07
    æľĢåĪĿ
    0.07
    ajo
    0.07
    ','','
    0.07
    original
    0.07
     оÑĢиг
    0.07
    Activations Density 0.020%

    No Known Activations