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. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5068
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context in sentences

    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
    ahl
    -0.07
    vi
    -0.06
    hev
    -0.06
    vala
    -0.06
    Īĺ
    -0.06
    .Protocol
    -0.06
    cheng
    -0.06
    panion
    -0.06
    ulle
    -0.06
    tod
    -0.06
    POSITIVE LOGITS
    elan
    0.09
    lander
    0.07
    endi
    0.07
    isd
    0.07
     Meg
    0.06
    emes
    0.06
    otten
    0.06
    landers
    0.06
    prec
    0.06
     meg
    0.06
    Activations Density 0.000%

    No Known Activations