© 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. 31096
    Prev
    Next
    INDEX
    Explanations

    affirmative statements and phrases indicating enjoyment or approval

    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
    aines
    -0.07
    omba
    -0.06
     ÐĴи
    -0.06
    esto
    -0.06
     reap
    -0.06
    ål
    -0.06
    apos
    -0.06
    inne
    -0.06
     Ole
    -0.06
    BarController
    -0.06
    POSITIVE LOGITS
     Lazy
    0.07
     strapon
    0.07
     rig
    0.07
    .qual
    0.07
    Lazy
    0.07
    ination
    0.06
    ereo
    0.06
    ÑĪки
    0.06
    ency
    0.06
     drill
    0.06
    Activations Density 0.003%

    No Known Activations