© 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. 92248
    Prev
    Next
    INDEX
    Explanations

    references to prominent figures and institutions in discussions about authority and leadership

    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
    ovation
    -0.07
    ignet
    -0.07
    ehr
    -0.07
    lichkeit
    -0.07
    egrity
    -0.07
    chter
    -0.07
    Bias
    -0.07
    oucher
    -0.06
    framework
    -0.06
    //{{
    -0.06
    POSITIVE LOGITS
    认为
    0.10
     felt
    0.09
     belief
    0.08
     believes
    0.08
     believe
    0.08
     believed
    0.08
     deemed
    0.08
     reasoning
    0.08
     wanted
    0.08
     simply
    0.07
    Activations Density 0.083%

    No Known Activations