© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2959
    Prev
    Next
    INDEX
    Explanations

    quantifiers indicating variety or diversity

    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
    -valu
    -0.08
    -assets
    -0.07
     Sır
    -0.06
    ÑĥÑĢÑģ
    -0.06
    IIIK
    -0.06
    äºĭæ¥Ń
    -0.06
    osu
    -0.06
    .vertx
    -0.06
    anh
    -0.06
    ymbols
    -0.06
    POSITIVE LOGITS
     others
    0.10
    others
    0.09
     other
    0.08
     assorted
    0.07
    HEMA
    0.07
     기íĥĢ
    0.07
     versions
    0.07
    other
    0.07
     dalÅ¡ÃŃch
    0.06
     eins
    0.06
    Activations Density 0.076%

    No Known Activations