© 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 EvalsExportsAPI 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. 85977
    Prev
    Next
    INDEX
    Explanations

    instances of the word "because" indicating causal reasoning or explanations

    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
     if
    -0.07
    ;
    -0.07
    iva
    -0.06
    :
    -0.06
    ike
    -0.06
     &
    -0.06
     when
    -0.06
    vt
    -0.06
    ãĥ©ãĥ¼
    -0.06
    vl
    -0.05
    POSITIVE LOGITS
    alet
    0.08
    ÑĥÑĩа
    0.08
    978
    0.08
     Nej
    0.07
    rame
    0.07
     there
    0.07
    untas
    0.07
     ìĤ¬ëŀĮìĿĢ
    0.07
    kus
    0.07
    ëŁŃ
    0.07
    Activations Density 0.026%

    No Known Activations