© 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. 93196
    Prev
    Next
    INDEX
    Explanations

    second person pronouns and their forms

    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
     Lev
    -0.06
    znik
    -0.05
     GetString
    -0.05
    ').'
    -0.05
     saturn
    -0.05
    FP
    -0.05
    anax
    -0.05
    JI
    -0.05
     rac
    -0.05
    /std
    -0.05
    POSITIVE LOGITS
     varsa
    0.09
     ever
    0.08
    ä»Ķ
    0.08
    fern
    0.07
    PMC
    0.07
    幸
    0.07
    593
    0.07
    527
    0.07
     nÃło
    0.07
    odian
    0.07
    Activations Density 0.023%

    No Known Activations