© 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. 69705
    Prev
    Next
    INDEX
    Explanations

    references to actions and decisions made by companies or organizations

    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
    ezi
    -0.08
    orno
    -0.08
    rear
    -0.08
    icina
    -0.07
    νÏĮ
    -0.07
    SKIP
    -0.07
     createState
    -0.07
    corn
    -0.07
    _GF
    -0.07
     AsyncCallback
    -0.06
    POSITIVE LOGITS
     decision
    0.07
    ban
    0.07
    roz
    0.06
    uid
    0.06
     Decision
    0.06
     listing
    0.06
    rompt
    0.06
    Iterator
    0.06
     sever
    0.06
     ban
    0.06
    Activations Density 0.010%

    No Known Activations