© 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. 119666
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the reduction or disintegration of structures or relationships

    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
    bian
    -0.10
    ysl
    -0.07
    isd
    -0.07
    Ïĩεί
    -0.07
    ekl
    -0.07
    зн
    -0.07
    нед
    -0.07
    éra
    -0.07
     dụng
    -0.07
    ourg
    -0.07
    POSITIVE LOGITS
    ed
    0.08
     barriers
    0.07
    sic
    0.07
    hoe
    0.06
     into
    0.06
    .scalablytyped
    0.06
    ilo
    0.06
    edly
    0.06
    375
    0.06
    eper
    0.06
    Activations Density 0.006%

    No Known Activations