© 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. 55897
    Prev
    Next
    INDEX
    Explanations

    references to dates and times

    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
    oli
    -0.07
    ãģ£ãģį
    -0.07
    .toObject
    -0.07
    eil
    -0.07
    ankan
    -0.07
    аки
    -0.07
    érc
    -0.06
    ÑģилÑĮ
    -0.06
    abbage
    -0.06
    ernal
    -0.06
    POSITIVE LOGITS
     XCT
    0.06
    ÑģÑĥÑĤ
    0.06
     Ferguson
    0.06
    à¥īà¤Ł
    0.06
    985
    0.06
    ãĤ´ãĥª
    0.06
    ÙĪرش
    0.06
     wise
    0.05
     Evelyn
    0.05
     ling
    0.05
    Activations Density 0.000%

    No Known Activations