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. 22-LLAMASCOPE-RES-131K
    6. 5498
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and web resource management

    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
    pas
    -0.07
    elen
    -0.06
     célib
    -0.06
    enstein
    -0.06
    hip
    -0.06
    razier
    -0.06
     Projection
    -0.06
    chen
    -0.06
    ester
    -0.06
    opus
    -0.06
    POSITIVE LOGITS
     Yuri
    0.07
     Adult
    0.07
     adult
    0.07
    .addElement
    0.07
    ụn
    0.07
     Meter
    0.06
    Rating
    0.06
    icÃŃ
    0.06
    енÑĥ
    0.06
    scores
    0.06
    Activations Density 0.001%

    No Known Activations