© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26514
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all" and variations of "process" or comprehensive inclusivity

    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
    aku
    -0.07
    enberg
    -0.06
    vr
    -0.06
     alone
    -0.06
     alter
    -0.06
    तर
    -0.06
    ior
    -0.06
     imper
    -0.06
    دÙĬØ«
    -0.05
     Farr
    -0.05
    POSITIVE LOGITS
     equally
    0.08
    uni
    0.08
    xCD
    0.08
    /full
    0.07
    alom
    0.07
    ollapse
    0.07
    mayan
    0.07
     accounted
    0.07
    orrect
    0.07
    orest
    0.07
    Activations Density 0.051%

    No Known Activations