© 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. 117645
    Prev
    Next
    INDEX
    Explanations

    expressions of hypothetical or conditional statements

    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
    ahat
    -0.08
    avec
    -0.07
     olursa
    -0.07
    ousand
    -0.07
    kud
    -0.06
    nameof
    -0.06
    illez
    -0.06
    eden
    -0.06
    prog
    -0.06
    urch
    -0.06
    POSITIVE LOGITS
     would
    0.17
    would
    0.15
     Would
    0.15
    Would
    0.15
     wouldn
    0.14
     Wouldn
    0.12
     hätte
    0.11
     seria
    0.10
    OULD
    0.10
     skulle
    0.10
    Activations Density 0.016%

    No Known Activations