© 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. 117000
    Prev
    Next
    INDEX
    Explanations

    sentiment and emotional reflections within personal anecdotes

    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
     VÅ¡ech
    -0.08
     célib
    -0.08
    Ấ
    -0.08
    .Minute
    -0.07
    _simps
    -0.07
    linkplain
    -0.07
    ustry
    -0.07
    usher
    -0.07
    insky
    -0.07
    oken
    -0.07
    POSITIVE LOGITS
     my
    0.06
     posts
    0.06
    gg
    0.06
     Dunn
    0.06
     finally
    0.05
    /html
    0.05
     me
    0.05
     blog
    0.05
     loop
    0.05
     post
    0.05
    Activations Density 1.450%

    No Known Activations