© 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. 78757
    Prev
    Next
    INDEX
    Explanations

    themes related to dietary restrictions and lifestyle changes

    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
    خش
    -0.07
    pipe
    -0.07
    iped
    -0.06
     acts
    -0.06
     shouldBe
    -0.06
     Sas
    -0.06
     èī¯
    -0.06
     should
    -0.06
     deber
    -0.06
     performan
    -0.06
    POSITIVE LOGITS
     replacements
    0.09
     substitutions
    0.08
    haul
    0.07
     cheats
    0.07
    465
    0.06
    åħ¥ãĤĮ
    0.06
     substitution
    0.06
    aju
    0.06
    vrier
    0.06
     замен
    0.06
    Activations Density 0.010%

    No Known Activations