© 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. 9-LLAMASCOPE-RES-131K
    11. 97446
    Prev
    Next
    INDEX
    Explanations

    references to changes in physical states or transformations

    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
    zte
    -0.08
    orer
    -0.07
    rieb
    -0.07
    stre
    -0.07
    ilton
    -0.07
    azio
    -0.07
    lla
    -0.07
    ITION
    -0.06
    alamat
    -0.06
    íļĮ
    -0.06
    POSITIVE LOGITS
    istry
    0.07
    rosse
    0.07
    .biz
    0.06
    æĿŁ
    0.06
     célib
    0.06
    otomy
    0.06
    éĢł
    0.06
     lucky
    0.06
    ucky
    0.06
    odox
    0.06
    Activations Density 0.002%

    No Known Activations