© 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. 129544
    Prev
    Next
    INDEX
    Explanations

    expressions of praise and appreciation for literature

    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
    anova
    -0.07
    eya
    -0.06
    Motion
    -0.06
    ัà¸Ķส
    -0.06
     squads
    -0.06
    astes
    -0.06
    è¼Ķ
    -0.05
    гал
    -0.05
    posed
    -0.05
    ='".
    -0.05
    POSITIVE LOGITS
     readers
    0.07
    opath
    0.06
    omet
    0.06
     Beste
    0.06
    -inner
    0.06
    elf
    0.06
    Prompt
    0.06
    sig
    0.06
    reads
    0.06
     trench
    0.06
    Activations Density 0.002%

    No Known Activations