© 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. 71614
    Prev
    Next
    INDEX
    Explanations

    references to the concept of existence or the absence of existence

    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
    λοÏħ
    -0.07
    inski
    -0.07
    IDD
    -0.07
    inki
    -0.07
    edii
    -0.06
    	Copyright
    -0.06
    .ide
    -0.06
    ilon
    -0.06
    utos
    -0.06
    izm
    -0.06
    POSITIVE LOGITS
     except
    0.08
     unless
    0.08
     anymore
    0.07
    alers
    0.07
    except
    0.07
    ä¸įåŃĺåľ¨
    0.06
    enden
    0.06
    itty
    0.06
    iegel
    0.06
    931
    0.06
    Activations Density 0.013%

    No Known Activations