© 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. 84667
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and entities, particularly in contexts related to authority or leadership

    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
    Äįka
    -0.09
    utin
    -0.08
    Äįky
    -0.08
    سÙĪب
    -0.07
    alars
    -0.07
    Äįku
    -0.07
    ifest
    -0.07
    emark
    -0.07
     addCriterion
    -0.07
    åı¤å±ĭ
    -0.07
    POSITIVE LOGITS
    pha
    0.06
    aman
    0.06
    ãĤ·ãĤ§
    0.06
     @"↵
    0.06
     Fried
    0.06
     pooled
    0.06
     Vul
    0.05
     finance
    0.05
    afort
    0.05
    enta
    0.05
    Activations Density 0.013%

    No Known Activations