© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82352
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or quantities

    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
    swick
    -0.07
    idor
    -0.07
    _RTC
    -0.07
    adro
    -0.07
     etwa
    -0.07
     Grip
    -0.07
    دار
    -0.07
    arrant
    -0.07
    arih
    -0.07
    holm
    -0.07
    POSITIVE LOGITS
    yper
    0.06
    geist
    0.06
    aya
    0.06
    uggy
    0.06
     Mystery
    0.06
     #@
    0.06
     Lawson
    0.06
    wap
    0.06
    agrams
    0.06
     gam
    0.06
    Activations Density 0.000%

    No Known Activations