© 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. 95823
    Prev
    Next
    INDEX
    Explanations

    references to trimming or adjustments, particularly in a contextual or structural sense

    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
    werp
    -0.07
     stron
    -0.07
    ients
    -0.07
    eenth
    -0.07
    hood
    -0.07
    åħ¥ãĤĮ
    -0.07
    fried
    -0.07
    ephy
    -0.06
    spring
    -0.06
    pire
    -0.06
    POSITIVE LOGITS
    mers
    0.08
    ming
    0.08
    uslim
    0.08
    licate
    0.07
    pered
    0.07
    med
    0.07
    mer
    0.07
    ting
    0.07
    ethyl
    0.07
    acock
    0.07
    Activations Density 0.006%

    No Known Activations