© 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. 81824
    Prev
    Next
    INDEX
    Explanations

    exclamation marks and other forms of emphasis or strong emotion in the text

    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
    loub
    -0.07
    antino
    -0.07
    edl
    -0.07
     buurt
    -0.07
    hz
    -0.06
    دÙĨ
    -0.06
    antro
    -0.06
    enko
    -0.06
    forcements
    -0.06
    rema
    -0.06
    POSITIVE LOGITS
    [](
    0.11
    uria
    0.07
    uries
    0.07
    DOCTYPE
    0.07
    µ¬
    0.07
    rious
    0.06
    QL
    0.06
    pron
    0.06
    eties
    0.06
    za
    0.06
    Activations Density 0.018%

    No Known Activations