© 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. 88863
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating progress or change

    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
     voks
    -0.07
    lien
    -0.06
    bbe
    -0.06
    ibaba
    -0.06
    .blog
    -0.06
    imd
    -0.06
    лÑİ
    -0.06
    å½ĵ
    -0.06
    acers
    -0.06
     tod
    -0.06
    POSITIVE LOGITS
    755
    0.07
    برÛĮ
    0.07
    625
    0.06
    lassen
    0.06
    ormal
    0.06
    antry
    0.06
     thì
    0.06
    ziaÅĤ
    0.06
    elf
    0.06
     ÙģØ¥ÙĨ
    0.06
    Activations Density 0.024%

    No Known Activations