© 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. 70857
    Prev
    Next
    INDEX
    Explanations

    references to theatrical plays

    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
    ierung
    -0.08
    erator
    -0.07
    657
    -0.07
    ÑģÑĮ
    -0.07
    롱
    -0.07
    lator
    -0.07
    etry
    -0.07
    ally
    -0.07
    icana
    -0.07
    451
    -0.07
    POSITIVE LOGITS
    offs
    0.10
    thing
    0.09
    wright
    0.09
    room
    0.09
    anan
    0.08
    ings
    0.08
    fulness
    0.08
    able
    0.08
    ableObject
    0.08
    alle
    0.08
    Activations Density 0.025%

    No Known Activations