© 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. 121339
    Prev
    Next
    INDEX
    Explanations

    references to voting and political processes

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

    Forum or Q&A platform formatting elements and punctuation that structure content, particularly timestamps, question marks, and navigation elements.

    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
    pit
    -0.08
    ró
    -0.07
    .blogspot
    -0.07
     Ferd
    -0.07
    illa
    -0.06
     Gü
    -0.06
    gren
    -0.06
    iran
    -0.06
    hausen
    -0.06
    ÏģÏĮ
    -0.06
    POSITIVE LOGITS
    eness
    0.07
    ability
    0.06
     Grimm
    0.06
    हर
    0.06
    .stack
    0.06
    455
    0.06
    IPA
    0.06
    âŁ
    0.06
    _PHYS
    0.06
    uer
    0.06
    Activations Density 0.025%

    No Known Activations