© 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. 16576
    Prev
    Next
    INDEX
    Explanations

    keywords related to government and political scandals

    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
    UTERS
    -0.08
    íĽĪ
    -0.07
    hev
    -0.07
     Truy
    -0.07
    ikal
    -0.07
     داد
    -0.07
    è¡Ģ
    -0.07
    üml
    -0.07
    /Admin
    -0.07
    erty
    -0.07
    POSITIVE LOGITS
    âĢĥ
    0.06
    oyal
    0.06
    Transition
    0.06
    ash
    0.06
    ward
    0.06
    clip
    0.06
    uto
    0.06
     unspecified
    0.06
    Unified
    0.05
    709
    0.05
    Activations Density 0.007%

    No Known Activations