© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86038
    Prev
    Next
    INDEX
    Explanations

    the emotional state and actions of a character

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    _ACL
    -0.07
    stdafx
    -0.07
    ãĥ©ãĤ¯
    -0.07
    ACES
    -0.06
    æĹıèĩªæ²»
    -0.06
    estre
    -0.06
    ì°©
    -0.06
    aylight
    -0.06
    æ°¸ä¹ħ
    -0.06
    .realm
    -0.06
    POSITIVE LOGITS
    icable
    0.07
    kw
    0.06
     Jet
    0.06
    IH
    0.06
    ropdown
    0.06
    tsy
    0.06
    [js
    0.06
    _quantity
    0.06
     ê¶ģê¸Ī
    0.06
    idf
    0.05
    Activations Density 0.000%

    No Known Activations