Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95782
    Prev
    Next
    INDEX
    Explanations

    references to influential figures and cultural movements in various fields

    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
    elow
    -0.10
    ulong
    -0.08
    neau
    -0.08
    ascript
    -0.07
    ELLOW
    -0.07
     Ekon
    -0.07
    .googleapis
    -0.07
    mand
    -0.07
    odem
    -0.07
    curacy
    -0.07
    POSITIVE LOGITS
     cupboard
    0.06
     Simply
    0.06
    apiro
    0.06
     suy
    0.05
    unker
    0.05
     exceeding
    0.05
     names
    0.05
     Koh
    0.05
     moist
    0.05
     crossover
    0.05
    Activations Density 0.029%

    No Known Activations