© 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. 15-LLAMASCOPE-RES-131K
    11. 87123
    Prev
    Next
    INDEX
    Explanations

    phrases that imply conditional statements or consequences

    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
    ungs
    -0.07
    -java
    -0.07
     unsafe
    -0.06
    amen
    -0.06
    kle
    -0.06
    kart
    -0.06
    engu
    -0.06
    atient
    -0.06
     Unsafe
    -0.06
    aman
    -0.06
    POSITIVE LOGITS
    898
    0.08
     when
    0.07
     VÅ¡
    0.07
    .sax
    0.07
     if
    0.07
     each
    0.07
    isme
    0.06
    akte
    0.06
    raž
    0.06
    458
    0.06
    Activations Density 0.013%

    No Known Activations