© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129549
    Prev
    Next
    INDEX
    Explanations

    themes related to accountability and reform in veterans' affairs

    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
    Ïħγ
    -0.08
     Aydın
    -0.08
    gaard
    -0.08
    ungle
    -0.07
    qué
    -0.07
    raison
    -0.07
    EATURE
    -0.07
    undle
    -0.07
    æ®Ĭ
    -0.07
    ceae
    -0.07
    POSITIVE LOGITS
     Administrator
    0.08
     unser
    0.07
     our
    0.06
     America
    0.06
     Brewer
    0.06
     shutter
    0.06
     --
    0.06
     precisely
    0.06
     exactly
    0.05
     -,
    0.05
    Activations Density 0.043%

    No Known Activations