© 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. 9-LLAMASCOPE-RES-131K
    11. 97509
    Prev
    Next
    INDEX
    Explanations

    references to political and governmental entities

    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
    icher
    -0.07
    icina
    -0.07
    inha
    -0.07
    uby
    -0.07
    steen
    -0.07
    iem
    -0.07
    uman
    -0.07
    chas
    -0.06
    tings
    -0.06
    opsis
    -0.06
    POSITIVE LOGITS
    .Butter
    0.07
    ãģ£ãģ±
    0.07
    typed
    0.06
    å©
    0.06
    {@
    0.06
     Wonderful
    0.06
     Lad
    0.06
    /***/
    0.06
    lÄ±ÅŁ
    0.06
    kı
    0.06
    Activations Density 0.018%

    No Known Activations