© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71012
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context in the 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
    .scalablytyped
    -0.07
    (Of
    -0.06
    upy
    -0.06
    iÄįky
    -0.06
    angel
    -0.06
     um
    -0.06
     Ansi
    -0.06
    ÙĨاد
    -0.06
    LIC
    -0.06
    Ùıر
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.09
    -badge
    0.08
    utterstock
    0.07
     damer
    0.07
    /from
    0.06
    akit
    0.06
    vere
    0.06
    bout
    0.06
    athon
    0.06
     tremend
    0.06
    Activations Density 0.064%

    No Known Activations