© 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. 84239
    Prev
    Next
    INDEX
    Explanations

    expressions conveying emphasis or degree

    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©ãĤ¯
    -0.08
     <!--[
    -0.07
    βο
    -0.06
    imits
    -0.06
    ÑģеÑĢ
    -0.06
    ÑģиÑĤ
    -0.06
    ñ
    -0.06
    tras
    -0.06
    ilik
    -0.06
    Gravity
    -0.06
    POSITIVE LOGITS
     so
    0.10
     sogar
    0.09
    çĶļèĩ³
    0.09
     наÑģÑĤ
    0.08
     enough
    0.07
     öyle
    0.07
     even
    0.07
     ÚĨÙĨاÙĨ
    0.07
    inge
    0.07
     extent
    0.07
    Activations Density 0.025%

    No Known Activations