© 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. 107102
    Prev
    Next
    INDEX
    Explanations

    concepts related to the Israeli-Palestinian conflict and discussions around peace processes

    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
    essian
    -0.08
    omens
    -0.08
    gan
    -0.08
    awning
    -0.07
    ButtonDown
    -0.07
    pga
    -0.07
    asma
    -0.07
     rebel
    -0.07
    KHR
    -0.07
    eyen
    -0.07
    POSITIVE LOGITS
    final
    0.06
    712
    0.06
    ewith
    0.06
    enis
    0.06
     final
    0.05
     Timing
    0.05
    IJ
    0.05
     Security
    0.05
    ãĤ·ãĥ§
    0.05
    acks
    0.05
    Activations Density 0.029%

    No Known Activations