© 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. 17-LLAMASCOPE-RES-131K
    11. 61587
    Prev
    Next
    INDEX
    Explanations

    instances of prominent subjects and their associated roles 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
     ApplicationException
    -0.07
    icros
    -0.07
    obia
    -0.07
    anye
    -0.07
    964
    -0.07
    esini
    -0.07
     traceback
    -0.06
    wick
    -0.06
    hood
    -0.06
    isha
    -0.06
    POSITIVE LOGITS
     incident
    0.07
    AuthProvider
    0.06
    ór
    0.06
    losures
    0.06
    rossover
    0.06
    onga
    0.06
    .mkdirs
    0.06
     change
    0.06
     man
    0.06
     decay
    0.05
    Activations Density 0.033%

    No Known Activations