© 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. 60861
    Prev
    Next
    INDEX
    Explanations

    mentions of popular social media platforms or websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    End-of-content markers that indicate transitions between different text blocks, including closing HTML tags, punctuation ending user content, URL components, and social media handles.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    yb
    -0.06
    emes
    -0.06
     Jar
    -0.06
     Shine
    -0.06
     Jacqu
    -0.06
     Gre
    -0.06
    à¸Ńม
    -0.06
    ieties
    -0.05
    æ¤į
    -0.05
    biz
    -0.05
    POSITIVE LOGITS
    razier
    0.07
     γλη
    0.07
    _LOADING
    0.07
     å£
    0.07
     EXIT
    0.07
    Porno
    0.07
    ัà¹Ī
    0.07
    rai
    0.07
     inher
    0.07
    illion
    0.07
    Activations Density 0.031%

    No Known Activations