© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93625
    Prev
    Next
    INDEX
    Explanations

    references to national security strategies and related documents

    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
    owards
    -0.07
    upil
    -0.06
     Templ
    -0.06
     leh
    -0.06
    oni
    -0.06
    kup
    -0.06
    Ñħи
    -0.06
     negoci
    -0.05
    εÏĤ
    -0.05
    ÙĪÙĪ
    -0.05
    POSITIVE LOGITS
    202
    0.08
    ingle
    0.07
    avel
    0.07
    OrNull
    0.07
    ikon
    0.06
     defaultMessage
    0.06
    ernals
    0.06
    atar
    0.06
    ẩn
    0.06
    aya
    0.06
    Activations Density 0.003%

    No Known Activations