© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14449
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

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

    A newline followed by two closing angle brackets, often appearing right after a code block, file path, URL, or at sentence boundaries, typically indicating the end of one section and beginning of another in structured text.

    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
    بÙĦ
    -0.07
    ooks
    -0.07
    AndGet
    -0.07
     yaÅŁÄ±nda
    -0.06
    uesto
    -0.06
    лиÑı
    -0.06
    ueblo
    -0.06
    ueba
    -0.06
     è¾
    -0.06
    endoza
    -0.06
    POSITIVE LOGITS
    cola
    0.06
    https
    0.06
    Ŀ
    0.06
    ecycle
    0.05
    weit
    0.05
    shares
    0.05
    croll
    0.05
     behold
    0.05
    found
    0.05
    cre
    0.05
    Activations Density 0.066%

    No Known Activations