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. 84340
    Prev
    Next
    INDEX
    Explanations

    phrases related to design concepts and outdoor spaces

    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
    .Extension
    -0.07
    .ERR
    -0.07
    ł
    -0.07
    ÙĨاÙĨ
    -0.07
    RelativeTo
    -0.07
    ÛĮدÛĮ
    -0.07
    िड
    -0.07
    ấc
    -0.07
     dazu
    -0.07
    IRM
    -0.07
    POSITIVE LOGITS
    afone
    0.06
    ieu
    0.06
     Thi
    0.06
     dis
    0.06
    aos
    0.06
    lys
    0.06
     BA
    0.05
     Brend
    0.05
    .nb
    0.05
     
    0.05
    Activations Density 0.001%

    No Known Activations