© 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. 104388
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and relational dynamics

    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
    endor
    -0.07
    anken
    -0.07
    ipop
    -0.06
     SID
    -0.06
    lesia
    -0.06
    enty
    -0.06
    CEPT
    -0.06
    uzzi
    -0.06
     Verfüg
    -0.06
     Pur
    -0.06
    POSITIVE LOGITS
     treated
    0.09
     priority
    0.07
    -treated
    0.07
    ongyang
    0.06
    .ops
    0.06
    priority
    0.06
     Mini
    0.06
    DownList
    0.06
     Priority
    0.06
     individual
    0.06
    Activations Density 0.015%

    No Known Activations