© 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. 107770
    Prev
    Next
    INDEX
    Explanations

    conditional phrases, particularly focusing on the word "whether."

    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
    etag
    -0.06
    ses
    -0.06
    VS
    -0.06
     ÙĪاÙĨ
    -0.06
    INVAL
    -0.06
    æľīä»Ģä¹Ī
    -0.06
     anything
    -0.06
     what
    -0.06
    ropp
    -0.06
    ãģį
    -0.05
    POSITIVE LOGITS
     Edwin
    0.07
    wert
    0.07
    ório
    0.07
    ableView
    0.07
    quete
    0.06
    ozo
    0.06
    ORY
    0.06
    ocos
    0.06
    uary
    0.06
    mpz
    0.06
    Activations Density 0.013%

    No Known Activations