© 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. 15-LLAMASCOPE-RES-131K
    11. 103133
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases that signify complex concepts or important elements in various contexts

    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
     Maid
    -0.06
     instead
    -0.06
     option
    -0.06
     damn
    -0.05
     Twins
    -0.05
     Dispatch
    -0.05
     NAFTA
    -0.05
     gang
    -0.05
     concerns
    -0.05
    329
    -0.05
    POSITIVE LOGITS
    Calibri
    0.08
    hee
    0.08
    Truthy
    0.08
    .XR
    0.08
    SocketAddress
    0.07
    WithTag
    0.07
    yre
    0.07
    -spacing
    0.07
    ñana
    0.07
    Clar
    0.07
    Activations Density 0.033%

    No Known Activations