© 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. 119920
    Prev
    Next
    INDEX
    Explanations

    terms related to specific artistic styles or characteristics

    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
    irit
    -0.08
    aphore
    -0.08
    imd
    -0.07
    -valu
    -0.07
    abay
    -0.07
    究
    -0.07
    dogs
    -0.07
    ÃŃrk
    -0.07
    .FontStyle
    -0.07
    terra
    -0.07
    POSITIVE LOGITS
    0.07
    pton
    0.06
     Miner
    0.06
    اتÙĩ
    0.06
     general
    0.06
    ople
    0.05
     Mo
    0.05
     Dut
    0.05
    ions
    0.05
     Higher
    0.05
    Activations Density 0.056%

    No Known Activations