Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76462
    Prev
    Next
    INDEX
    Explanations

    references to competition and user engagement in social media

    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
    ancel
    -0.07
    ocz
    -0.07
    Ģ
    -0.07
    afort
    -0.06
    ilda
    -0.06
    pson
    -0.06
    ledon
    -0.06
     Adler
    -0.06
     Magn
    -0.06
    Advertisement
    -0.06
    POSITIVE LOGITS
     Social
    0.08
    agram
    0.08
     social
    0.07
    ìĨĮëħĦ
    0.07
    Social
    0.07
     Heap
    0.07
     SOCIAL
    0.07
    ennie
    0.06
    isan
    0.06
     content
    0.06
    Activations Density 0.002%

    No Known Activations