© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26712
    Prev
    Next
    INDEX
    Explanations

    phrases related to social help and community engagement efforts

    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
    AZY
    -0.08
    acco
    -0.07
    chwitz
    -0.07
     Gry
    -0.07
    .setToolTipText
    -0.07
    byt
    -0.06
    ilis
    -0.06
    yar
    -0.06
    BIT
    -0.06
    ACHI
    -0.06
    POSITIVE LOGITS
     foreign
    0.08
    landa
    0.08
    ument
    0.07
     Foreign
    0.07
     local
    0.07
     aid
    0.07
     parach
    0.06
    aid
    0.06
     abroad
    0.06
    มาย
    0.06
    Activations Density 0.009%

    No Known Activations