© 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. 5544
    Prev
    Next
    INDEX
    Explanations

    words indicating quantities or measures

    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
    sburg
    -0.08
    acas
    -0.08
    tempt
    -0.07
    xit
    -0.07
    ifo
    -0.07
    nof
    -0.07
    thon
    -0.07
    _DELTA
    -0.06
    awl
    -0.06
    کر
    -0.06
    POSITIVE LOGITS
     Miner
    0.06
     twin
    0.06
     пÑĥнкÑĤ
    0.06
     areas
    0.06
    TA
    0.06
    WithString
    0.06
     Mold
    0.06
     mans
    0.06
     Suc
    0.06
     per
    0.06
    Activations Density 0.001%

    No Known Activations