© 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. 117855
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" in various contexts

    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
     zwar
    -0.08
    èĻ½
    -0.08
    aday
    -0.07
    adu
    -0.07
    -fontawesome
    -0.07
    èĻ½çĦ¶
    -0.07
    amil
    -0.07
    ypi
    -0.07
    anium
    -0.07
    amac
    -0.07
    POSITIVE LOGITS
     somehow
    0.11
     irgend
    0.07
     necessarily
    0.07
    odd
    0.07
     anybody
    0.07
     magically
    0.06
    /how
    0.06
     anyone
    0.06
    زر
    0.06
    é¦
    0.06
    Activations Density 0.029%

    No Known Activations