© 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. 95562
    Prev
    Next
    INDEX
    Explanations

    references to specific names and brands related to music and media

    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
    UME
    -0.08
    raci
    -0.07
     Cups
    -0.07
    orie
    -0.07
    bound
    -0.06
    éru
    -0.06
     treff
    -0.06
    prü
    -0.06
    ently
    -0.06
    weapons
    -0.06
    POSITIVE LOGITS
    ular
    0.09
    lero
    0.09
    erna
    0.08
    loid
    0.08
    ulous
    0.07
    asaki
    0.07
    /tab
    0.07
    ernes
    0.07
    oul
    0.07
    ler
    0.07
    Activations Density 0.010%

    No Known Activations