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. 44234
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to the concept of "emphatic" or emphasized points in theorems or proofs

    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
    en
    -0.08
    ener
    -0.08
    servers
    -0.07
    eners
    -0.07
    sdale
    -0.07
    sar
    -0.07
    arian
    -0.07
    sing
    -0.07
    aroo
    -0.07
    iates
    -0.07
    POSITIVE LOGITS
    ph
    0.21
    itet
    0.10
    pl
    0.09
    phant
    0.09
    PH
    0.09
    phem
    0.09
    phas
    0.09
    phasis
    0.08
    pm
    0.08
    pth
    0.08
    Activations Density 0.010%

    No Known Activations