© 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. 39357
    Prev
    Next
    INDEX
    Explanations

    the phrase "you will ever" and similar constructions that suggest a strong claim or promise

    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
    manifest
    -0.07
    jours
    -0.07
    ué
    -0.07
    ç¶Ń
    -0.06
    undi
    -0.06
    quette
    -0.06
    Disposed
    -0.06
    ilon
    -0.06
    åĸ¶
    -0.06
     Dish
    -0.06
    POSITIVE LOGITS
     encounter
    0.07
    uart
    0.07
    ppo
    0.06
     encounters
    0.06
    erno
    0.06
    uar
    0.06
     encountering
    0.06
    .Views
    0.06
    antro
    0.06
     Inspir
    0.06
    Activations Density 0.006%

    No Known Activations