© 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. 5507
    Prev
    Next
    INDEX
    Explanations

    terms related to government accountability and oversight

    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
    εκ
    -0.08
    ÄŁan
    -0.07
    EEK
    -0.07
    okane
    -0.07
    วล
    -0.07
    ocha
    -0.07
    OLDER
    -0.07
    avia
    -0.07
    rol
    -0.07
    hek
    -0.07
    POSITIVE LOGITS
     shall
    0.08
     study
    0.07
    shall
    0.07
     report
    0.07
     shalt
    0.07
    0.06
     SHALL
    0.06
     forth
    0.06
     annually
    0.06
     sunset
    0.06
    Activations Density 0.032%

    No Known Activations