© 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. 80203
    Prev
    Next
    INDEX
    Explanations

    elements related to duration and continuity in narratives or experiences

    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
     new
    -0.06
    otes
    -0.06
     Holt
    -0.05
    779
    -0.05
     height
    -0.05
    307
    -0.05
    alter
    -0.05
    won
    -0.05
    ocy
    -0.05
    Church
    -0.05
    POSITIVE LOGITS
     longest
    0.17
     longevity
    0.15
     Longer
    0.13
     longer
    0.13
    ยาว
    0.10
     dÃłi
    0.10
     lâu
    0.10
     Ø·ÙĪÙĦ
    0.10
    éķ·
    0.10
     prolonged
    0.09
    Activations Density 0.028%

    No Known Activations