© 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 EvalsExportsAPI 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. 119232
    Prev
    Next
    INDEX
    Explanations

    references to governmental or organizational actions and legal implications

    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
    ASSES
    -0.06
    agus
    -0.06
     gó
    -0.06
    Ë
    -0.06
     flush
    -0.06
    dorf
    -0.06
     Credit
    -0.06
    aptop
    -0.05
     alc
    -0.05
     spell
    -0.05
    POSITIVE LOGITS
    eden
    0.08
    :request
    0.08
    Requests
    0.07
    requests
    0.07
     requests
    0.07
    _requests
    0.07
    uki
    0.07
    LOBAL
    0.07
    \Active
    0.07
     Requests
    0.07
    Activations Density 0.000%

    No Known Activations