© 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. 89520
    Prev
    Next
    INDEX
    Explanations

    specific choices and decisions made by characters

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

    Words and phrases that serve as narrative transitions or connectors between different parts of text, often preceding punctuation or introducing a new clause.

    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
    CDATA
    -0.08
    cott
    -0.08
    .spec
    -0.07
    ãģ²
    -0.07
    lád
    -0.07
    569
    -0.07
    azy
    -0.07
    aison
    -0.07
    andy
    -0.07
    ENO
    -0.07
    POSITIVE LOGITS
     latter
    0.14
     choice
    0.08
     whichever
    0.08
     choose
    0.08
     option
    0.08
     Latter
    0.08
     former
    0.08
     opt
    0.07
     chose
    0.07
    choose
    0.07
    Activations Density 0.040%

    No Known Activations