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

    Neuronpedia

    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. 39722
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary verbs related to second-person and first-person perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ibold
    -0.07
    .advance
    -0.07
    åĴ²
    -0.07
    arend
    -0.07
    obili
    -0.07
    embros
    -0.07
     rozs
    -0.07
    æħĭ
    -0.07
    zych
    -0.07
    kie
    -0.07
    POSITIVE LOGITS
     will
    0.10
     might
    0.09
     may
    0.09
    'll
    0.09
     chances
    0.08
    will
    0.08
    ’ll
    0.08
     can
    0.08
     should
    0.08
    å°±ä¼ļ
    0.08
    Activations Density 0.034%

    No Known Activations