© 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 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. 119303
    Prev
    Next
    INDEX
    Explanations

    information about individuals' professional backgrounds, achievements, and expertise

    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
    Č
    -0.08
    aland
    -0.07
    alamat
    -0.07
    anta
    -0.07
    elligent
    -0.07
    ocrat
    -0.07
    orthand
    -0.07
    stial
    -0.07
    fty
    -0.07
    uder
    -0.07
    POSITIVE LOGITS
     rel
    0.07
    èĪ
    0.07
    é¾
    0.06
    ichel
    0.06
     quant
    0.05
    åŀĭ
    0.05
    jong
    0.05
     [âĢ¦
    0.05
     award
    0.05
    rite
    0.05
    Activations Density 0.007%

    No Known Activations