© 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. 78574
    Prev
    Next
    INDEX
    Explanations

    actions related to engaging with social media and online presence

    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
    áž
    -0.07
    ulta
    -0.07
    435
    -0.06
    èĪ
    -0.06
     pil
    -0.06
    Consumer
    -0.06
    ult
    -0.06
    Strict
    -0.06
    796
    -0.06
     Strict
    -0.06
    POSITIVE LOGITS
    website
    0.08
     website
    0.08
     his
    0.07
    enko
    0.07
    bsite
    0.07
     Website
    0.07
    Website
    0.07
     mimo
    0.07
     websites
    0.07
    nez
    0.06
    Activations Density 0.018%

    No Known Activations