© 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. 74483
    Prev
    Next
    INDEX
    Explanations

    statements involving personal pronouns and their associated actions or thoughts

    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
    isÃŃ
    -0.08
    ÄĻ
    -0.07
    kowski
    -0.07
    (æĹ¥
    -0.07
    odate
    -0.07
    rone
    -0.07
    olle
    -0.07
    erece
    -0.07
    ̧
    -0.07
    à¸
    -0.07
    POSITIVE LOGITS
    eter
    0.07
     ultimate
    0.07
     term
    0.07
    ulet
    0.06
    aves
    0.06
     incident
    0.06
    urd
    0.06
     must
    0.06
    anger
    0.06
     can
    0.06
    Activations Density 0.033%

    No Known Activations