© 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. 129450
    Prev
    Next
    INDEX
    Explanations

    references to incidents or experiences with negative consequences

    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
    oley
    -0.07
    anium
    -0.06
    ÄĽn
    -0.06
     Pitch
    -0.06
    Ã¶ÄŁ
    -0.06
     WCHAR
    -0.06
    podob
    -0.06
    PURE
    -0.06
    Weak
    -0.06
    ızı
    -0.06
    POSITIVE LOGITS
     earlier
    0.15
    åĪļæīį
    0.10
     aforementioned
    0.10
    Earlier
    0.09
     Earlier
    0.09
     previous
    0.08
     previously
    0.07
    EGIN
    0.07
     вÑĭÑĪе
    0.07
    ãģĤãģ®
    0.07
    Activations Density 0.024%

    No Known Activations