© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18573
    Prev
    Next
    INDEX
    Explanations

    references to specific scenes or notable moments in narratives

    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
     PSG
    -0.05
    ander
    -0.05
     Panda
    -0.05
    STRU
    -0.05
    ANC
    -0.05
    ousse
    -0.05
    æ³ķ人
    -0.05
     grade
    -0.05
    oval
    -0.05
     vs
    -0.05
    POSITIVE LOGITS
    callbacks
    0.08
    atÃŃm
    0.07
    ynamics
    0.07
    slash
    0.07
    pcf
    0.07
    خش
    0.07
    ÚĨÙĩ
    0.07
     glyphicon
    0.07
    ep
    0.07
     DEALINGS
    0.07
    Activations Density 0.003%

    No Known Activations