© 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. 14679
    Prev
    Next
    INDEX
    Explanations

    references to educational or academic 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
    ekk
    -0.07
    idlo
    -0.07
    uff
    -0.07
    -badge
    -0.07
     adipiscing
    -0.07
    beck
    -0.07
    åĿĬ
    -0.06
    rief
    -0.06
    isci
    -0.06
    quito
    -0.06
    POSITIVE LOGITS
     Google
    0.10
     google
    0.09
     Wikipedia
    0.09
    .google
    0.09
     internet
    0.08
    google
    0.08
     library
    0.08
     online
    0.08
     GOOGLE
    0.08
     wikipedia
    0.07
    Activations Density 0.048%

    No Known Activations