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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43834
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to specific numerical or statistical data

    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
    Houston
    -0.08
    ouston
    -0.08
     Houston
    -0.08
     Calgary
    -0.08
    Seattle
    -0.08
     Bermuda
    -0.07
     Brisbane
    -0.07
     Lagos
    -0.07
     NGX
    -0.07
     Seattle
    -0.07
    POSITIVE LOGITS
     Illinois
    0.24
    Ill
    0.19
     Ill
    0.17
     IL
    0.17
     Il
    0.14
    ILL
    0.13
     Springfield
    0.13
    _IL
    0.12
    IL
    0.12
     ID
    0.12
    Activations Density 0.002%

    No Known Activations