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. 43523
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols 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
    antor
    -0.06
    ivor
    -0.06
    educt
    -0.06
     architectural
    -0.06
    amel
    -0.06
    GLOBALS
    -0.06
    ÑĦоÑĢми
    -0.06
    cart
    -0.06
     globalization
    -0.06
     Lyft
    -0.06
    POSITIVE LOGITS
     Cav
    0.12
     equipment
    0.10
     apparatus
    0.09
     counts
    0.09
     Equipment
    0.09
    Equipment
    0.08
     replication
    0.08
     replicate
    0.08
     measurements
    0.08
     repro
    0.08
    Activations Density 0.004%

    No Known Activations