© 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 EvalsExportsAPI 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. 78319
    Prev
    Next
    INDEX
    Explanations

    conditional expressions of desire or preference

    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
    ijken
    -0.07
    imei
    -0.07
    ioni
    -0.07
    isset
    -0.07
    ernet
    -0.07
    duk
    -0.06
    akens
    -0.06
    ubi
    -0.06
    ibo
    -0.06
    FFE
    -0.06
    POSITIVE LOGITS
     prefer
    0.07
     preference
    0.07
     Stout
    0.06
    Pref
    0.06
    @if
    0.06
     Amber
    0.06
    .like
    0.06
     pref
    0.06
     neat
    0.06
     trust
    0.05
    Activations Density 0.025%

    No Known Activations