© 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. 54229
    Prev
    Next
    INDEX
    Explanations

    connections between actions and consequences in narratives, particularly involving commitment and trust

    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
    ãĤ¤ãĥĦ
    -0.07
    ãĥĥãĥĦ
    -0.07
    abis
    -0.07
    å¤ĩ
    -0.07
    iž
    -0.07
    hardware
    -0.06
    StackNavigator
    -0.06
    аÑĢÑĩ
    -0.06
    usta
    -0.06
    $MESS
    -0.06
    POSITIVE LOGITS
     agree
    0.08
     promise
    0.08
    é¡ĺ
    0.07
     guaranteed
    0.07
     Promise
    0.07
     guarantee
    0.07
     Agree
    0.06
     promising
    0.06
    promise
    0.06
     promises
    0.06
    Activations Density 0.032%

    No Known Activations