© 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. 105189
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases that highlight qualities or features of music and films

    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
    ÂĿ
    -0.06
    herits
    -0.06
    hil
    -0.06
    whel
    -0.06
    hib
    -0.06
    XL
    -0.06
    ware
    -0.06
    uno
    -0.05
    achel
    -0.05
    ardin
    -0.05
    POSITIVE LOGITS
     combination
    0.09
    stood
    0.09
    combination
    0.08
    elden
    0.08
     emphasis
    0.08
    LOPT
    0.08
     attendant
    0.07
    ANNEL
    0.07
    tout
    0.07
    ëĭ´
    0.07
    Activations Density 0.013%

    No Known Activations