© 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. 108184
    Prev
    Next
    INDEX
    Explanations

    instances of medical or legal advice and actions taken by authorities

    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
    apur
    -0.07
    TRACE
    -0.07
     repro
    -0.07
    ãģĭãģĹ
    -0.07
    \Php
    -0.06
    abis
    -0.06
    228
    -0.06
    ارÙĩ
    -0.06
    _rt
    -0.06
    alm
    -0.06
    POSITIVE LOGITS
    以为
    0.10
     expectation
    0.09
     believed
    0.09
     expecting
    0.08
     belief
    0.08
     believing
    0.08
    belief
    0.08
     believe
    0.08
     expectations
    0.08
     unaware
    0.08
    Activations Density 0.079%

    No Known Activations