© 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. 55576
    Prev
    Next
    INDEX
    Explanations

    phrases related to nature, specifically grass

    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
    omik
    -0.10
    oker
    -0.08
    ebi
    -0.08
    enler
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
     Truy
    -0.07
    alamat
    -0.07
    kü
    -0.07
    bject
    -0.07
    buat
    -0.07
    POSITIVE LOGITS
     rov
    0.06
    cn
    0.05
     kal
    0.05
     Roberts
    0.05
    à¹Ģว
    0.05
     ab
    0.05
     cocks
    0.05
     Ding
    0.05
     Likes
    0.05
    ced
    0.05
    Activations Density 0.000%

    No Known Activations