© 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. 105635
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context in sentences

    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
    inton
    -0.07
     Minute
    -0.06
    ottie
    -0.06
    ajo
    -0.06
    à¤Łà¤ķ
    -0.06
    imenti
    -0.06
    aku
    -0.06
    inx
    -0.06
    aland
    -0.06
     petit
    -0.06
    POSITIVE LOGITS
    mast
    0.09
    oux
    0.07
    NECT
    0.07
    олаг
    0.07
     frontal
    0.06
     Fro
    0.06
    ifies
    0.06
    оÑĤоÑĢ
    0.06
    åľŁ
    0.06
    STYPE
    0.06
    Activations Density 0.001%

    No Known Activations