© 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. 5-LLAMASCOPE-RES-131K
    11. 125988
    Prev
    Next
    INDEX
    Explanations

    references to statehood and discussions surrounding nationhood

    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
     fed
    -0.06
    ativa
    -0.06
    Äı
    -0.06
    sei
    -0.06
    iena
    -0.06
    é¦
    -0.06
     copies
    -0.06
     Copies
    -0.06
    iers
    -0.06
     Scientist
    -0.06
    POSITIVE LOGITS
    _simps
    0.06
    áp
    0.06
    edx
    0.06
    å¿Ĺ
    0.06
     condi
    0.06
    .espresso
    0.06
    bitset
    0.06
    erif
    0.06
     æ¥
    0.06
    npos
    0.06
    Activations Density 0.000%

    No Known Activations