© 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. 94494
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and phrases that express enjoyment of 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
    amin
    -0.06
     che
    -0.06
     Rice
    -0.06
    essler
    -0.06
     lij
    -0.05
    -l
    -0.05
    acky
    -0.05
    åĹ
    -0.05
     susp
    -0.05
    foil
    -0.05
    POSITIVE LOGITS
    _rating
    0.07
    paces
    0.07
     âĺĨ
    0.07
    åł
    0.07
    oti
    0.07
     Atl
    0.07
    Rating
    0.07
    á»Ļt
    0.07
    recommended
    0.07
     Rating
    0.07
    Activations Density 0.022%

    No Known Activations