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. 11444
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters often used in mathematical or scientific contexts

    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
    ableViewController
    -0.07
    ftware
    -0.06
     IS
    -0.06
     Resources
    -0.06
    NSBundle
    -0.06
    udios
    -0.06
     Roberts
    -0.06
     Mill
    -0.06
    URLException
    -0.06
     instance
    -0.05
    POSITIVE LOGITS
    /container
    0.08
    ARI
    0.08
    .container
    0.08
    Switch
    0.07
    -container
    0.07
     Container
    0.07
    Container
    0.07
    "default
    0.07
    For
    0.07
    Template
    0.07
    Activations Density 0.003%

    No Known Activations