© 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. 120215
    Prev
    Next
    INDEX
    Explanations

    phrases introducing conditional scenarios

    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
    leigh
    -0.06
    swire
    -0.06
    opic
    -0.06
     Lopez
    -0.06
    jo
    -0.06
    sv
    -0.06
     disemb
    -0.06
    ointed
    -0.06
    lett
    -0.06
    jak
    -0.06
    POSITIVE LOGITS
    LTR
    0.09
     you
    0.08
     your
    0.08
     ваÑģ
    0.07
     youre
    0.07
    phe
    0.07
    azen
    0.07
    ä½ł
    0.07
    itsu
    0.07
    _Utils
    0.07
    Activations Density 0.007%

    No Known Activations