© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56049
    Prev
    Next
    INDEX
    Explanations

    content related to philosophical theories and essays

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

    References to essay writing services, academic citations, and paper-for-hire websites, including domain names, citation formats, and service descriptions.

    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
    isko
    -0.07
    Verse
    -0.06
     silk
    -0.06
    upal
    -0.06
    krom
    -0.06
    ãĥ¼ãĥĨ
    -0.06
    .att
    -0.06
     patents
    -0.06
    quia
    -0.06
     Sab
    -0.05
    POSITIVE LOGITS
    essay
    0.11
     essay
    0.11
    Essay
    0.09
     Essay
    0.09
     essays
    0.09
     assignment
    0.09
     Essays
    0.09
    论æĸĩ
    0.08
    assignment
    0.08
    代
    0.08
    Activations Density 0.300%

    No Known Activations