© 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. 86453
    Prev
    Next
    INDEX
    Explanations

    numerical data and mentions of transactions

    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
    >NN
    -0.07
    urum
    -0.07
    baum
    -0.07
     Lux
    -0.06
    onian
    -0.06
     Tip
    -0.06
     Phoenix
    -0.05
    GLOBALS
    -0.05
    uros
    -0.05
    $MESS
    -0.05
    POSITIVE LOGITS
    ãİ
    0.08
    ãĥ¼ãĥĨ
    0.08
    ampo
    0.07
    ingo
    0.07
     clock
    0.07
     pochop
    0.06
    ÙĪÙĬÙĦ
    0.06
    uft
    0.06
     tiener
    0.06
    _hooks
    0.06
    Activations Density 0.000%

    No Known Activations