© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 5187
    Prev
    Next
    INDEX
    Explanations

    specific names and identifiers related to people and institutions

    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
    abox
    -0.09
    auer
    -0.09
    ialized
    -0.08
    -aos
    -0.08
    edis
    -0.08
    GINE
    -0.08
    âĹıâĹıâĹıâĹı
    -0.08
    963
    -0.08
    çIJ³
    -0.08
    Illuminate
    -0.07
    POSITIVE LOGITS
     Sor
    0.06
    son
    0.06
     “
    0.06
    t
    0.05
     Inner
    0.05
     sor
    0.05
    ç½®
    0.05
     felt
    0.05
     fed
    0.05
     Kumar
    0.05
    Activations Density 0.091%

    No Known Activations