© 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. 15-LLAMASCOPE-RES-131K
    6. 1101
    Prev
    Next
    INDEX
    Explanations

    metrics related to user engagement and growth in technology-focused applications

    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
    arra
    -0.07
    phan
    -0.07
    .newBuilder
    -0.07
    ament
    -0.07
    otu
    -0.07
    eus
    -0.07
    conv
    -0.06
    ãĤ¹ãĤ¯
    -0.06
    izzle
    -0.06
    BOOST
    -0.06
    POSITIVE LOGITS
     global
    0.08
     users
    0.07
    407
    0.07
    global
    0.07
     daily
    0.06
     worldwide
    0.06
     user
    0.06
     monthly
    0.06
     base
    0.06
    406
    0.06
    Activations Density 0.010%

    No Known Activations