© 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. 131028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only," particularly when it suggests limitations or exceptions

    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
    486
    -0.08
     nor
    -0.07
    ogan
    -0.06
    รà¸ĵ
    -0.06
    UNC
    -0.06
    jt
    -0.06
    lang
    -0.06
    fait
    -0.06
    EV
    -0.06
    cen
    -0.06
    POSITIVE LOGITS
     because
    0.09
    because
    0.07
    _TestCase
    0.07
    Because
    0.07
    ÙĨدگÛĮ
    0.07
    为äºĨ
    0.07
    \AppData
    0.07
    ãĥĥãĥĹ
    0.06
    _READONLY
    0.06
     omdat
    0.06
    Activations Density 0.006%

    No Known Activations