© 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. 28852
    Prev
    Next
    INDEX
    Explanations

    concepts related to equality and patriotism

    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
    stra
    -0.08
    unc
    -0.07
    akis
    -0.07
    iset
    -0.07
    eri
    -0.07
    ao
    -0.07
     Til
    -0.06
    ker
    -0.06
    445
    -0.06
    enc
    -0.06
    POSITIVE LOGITS
     Revolutionary
    0.07
     Natural
    0.06
    лами
    0.06
    StyleSheet
    0.06
    .qq
    0.06
    .od
    0.06
     ÐĶеÑĢжав
    0.06
    ëŀĮ
    0.06
     Blow
    0.06
    -toggler
    0.06
    Activations Density 0.002%

    No Known Activations