© 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. 126735
    Prev
    Next
    INDEX
    Explanations

    contractions of the word "will" and "would"

    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
    _DYNAMIC
    -0.06
    /or
    -0.06
    avadoc
    -0.06
    gren
    -0.06
    ismet
    -0.06
    /al
    -0.06
    isation
    -0.06
    icot
    -0.06
     Pell
    -0.06
    liest
    -0.06
    POSITIVE LOGITS
    jang
    0.07
     LEN
    0.07
    nbsp
    0.07
    거리
    0.06
    utow
    0.06
    Lorem
    0.06
    xbd
    0.06
    ÙħاÙĨÛĮ
    0.06
    inear
    0.06
     Shr
    0.06
    Activations Density 0.006%

    No Known Activations