© 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. 5629
    Prev
    Next
    INDEX
    Explanations

    procedural or instructional elements related to software usage and installation processes

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

    Punctuation marks that appear at the start of procedural instructions or steps, often following section headers like "PREPARATION", "How to use the exploit", or explanatory text that introduces a process or method.

    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
    ãĥ³ãĥIJ
    -0.07
    arter
    -0.07
    Ģìŀ¥
    -0.07
    ISTORY
    -0.06
    riterion
    -0.06
    mÃŃt
    -0.06
    oulouse
    -0.06
     eBooks
    -0.06
     numberOfRowsInSection
    -0.06
    ultz
    -0.06
    POSITIVE LOGITS
     first
    0.12
     First
    0.11
    First
    0.10
    first
    0.10
     simply
    0.08
    наÑĩала
    0.08
     fist
    0.08
     ãģ¾
    0.07
     firstly
    0.07
     اÙĪÙĦ
    0.07
    Activations Density 0.039%

    No Known Activations