© 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. 5-LLAMASCOPE-RES-131K
    11. 126726
    Prev
    Next
    INDEX
    Explanations

    instances of repetition or emphasis in phrasing

    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
    inand
    -0.07
    res
    -0.06
    obo
    -0.06
     Pearce
    -0.06
    night
    -0.06
    ast
    -0.06
    illon
    -0.06
    ágenes
    -0.06
    ouv
    -0.06
    ling
    -0.06
    POSITIVE LOGITS
    ecta
    0.08
    VML
    0.07
    é¨
    0.07
    ATEGORY
    0.07
    ABCDEFGHIJKLMNOP
    0.07
    اسÙĬ
    0.07
    abcdefghijklmnop
    0.07
    İ
    0.06
    PTY
    0.06
    696
    0.06
    Activations Density 0.001%

    No Known Activations