© 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. 119359
    Prev
    Next
    INDEX
    Explanations

    sections of academic texts related to abstracts or thematic summaries

    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
    .firebaseapp
    -0.07
    ldkf
    -0.07
    öyle
    -0.07
    oldem
    -0.07
    chten
    -0.07
    yb
    -0.07
    çak
    -0.07
    ialis
    -0.07
    åij
    -0.06
    ç
    -0.06
    POSITIVE LOGITS
    itone
    0.07
     offline
    0.07
    uter
    0.06
     Turnbull
    0.06
    ,
    0.06
    opis
    0.06
     boot
    0.06
    estyle
    0.06
    .
    0.06
    utron
    0.05
    Activations Density 0.001%

    No Known Activations