© 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. 129954
    Prev
    Next
    INDEX
    Explanations

    occurrences and repetitions of words, numbers, and punctuation in text

    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
    long
    -0.06
    976
    -0.06
    ansion
    -0.06
     Establishment
    -0.06
    panion
    -0.05
    éģ
    -0.05
    abbr
    -0.05
    ÙĪرش
    -0.05
    lett
    -0.05
    824
    -0.05
    POSITIVE LOGITS
     within
    0.09
     anywhere
    0.09
     trong
    0.09
    within
    0.08
     occurrences
    0.08
     appearing
    0.08
     throughout
    0.08
     dalam
    0.08
     present
    0.08
     presente
    0.08
    Activations Density 0.039%

    No Known Activations