© 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 EvalsExportsinterp-engineNEWAPI 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. 124797
    Prev
    Next
    INDEX
    Explanations

    occurrences of personal pronouns and their conjugations

    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
    alt
    -0.07
    Æ°á»Ľ
    -0.07
    ứ
    -0.06
    auc
    -0.06
    çļĦæĺ¯
    -0.06
     precisely
    -0.06
    kins
    -0.06
    dbcTemplate
    -0.06
    大家
    -0.06
    åīĽ
    -0.06
    POSITIVE LOGITS
     then
    0.12
     continued
    0.11
    continued
    0.09
     next
    0.09
     later
    0.09
     soon
    0.09
    	then
    0.08
    Then
    0.08
     THEN
    0.08
     então
    0.08
    Activations Density 0.028%

    No Known Activations