© 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. 129729
    Prev
    Next
    INDEX
    Explanations

    phrases indicating web content and legal disclaimers

    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
    èĪĪ
    -0.06
    AGER
    -0.06
    burger
    -0.06
     Burg
    -0.05
    ples
    -0.05
    @qq
    -0.05
    pus
    -0.05
    atrice
    -0.05
     Huffington
    -0.05
    iones
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.07
     ово
    0.07
    #
    0.07
    edl
    0.07
    elper
    0.07
    FRING
    0.07
    )did
    0.07
     pages
    0.07
     website
    0.07
    osc
    0.07
    Activations Density 0.004%

    No Known Activations