© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118908
    Prev
    Next
    INDEX
    Explanations

    references to literary awards and nominations

    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
     Journal
    -0.07
    ikel
    -0.07
     Freeze
    -0.06
    esini
    -0.06
     freeze
    -0.06
    anlar
    -0.06
    ignon
    -0.06
    Journal
    -0.06
    -Pro
    -0.06
     REFER
    -0.06
    POSITIVE LOGITS
     Booker
    0.09
    нез
    0.07
     chod
    0.06
    rial
    0.06
     trao
    0.06
    enos
    0.06
    ,{"
    0.06
     polling
    0.06
    ipur
    0.06
    pus
    0.06
    Activations Density 0.009%

    No Known Activations