© 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. 4557
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly of individuals

    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
     Güven
    -0.08
    .tiles
    -0.07
    gratis
    -0.07
    	throws
    -0.07
    οÏħÏģγ
    -0.06
    ï¼ľ
    -0.06
     ô
    -0.06
    åĩºãģĹ
    -0.06
    .dk
    -0.06
    .lt
    -0.06
    POSITIVE LOGITS
     freelance
    0.06
    ksam
    0.06
    EditingController
    0.06
    eden
    0.06
    vas
    0.06
     is
    0.06
    standen
    0.06
     crossorigin
    0.06
    ceae
    0.06
    éry
    0.06
    Activations Density 0.008%

    No Known Activations