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. 5065
    Prev
    Next
    INDEX
    Explanations

    phrases indicating absence or the concept of "no."

    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
    æ·
    -0.07
    uct
    -0.06
    357
    -0.06
    erson
    -0.06
    logan
    -0.06
    èĻŁ
    -0.06
    qrt
    -0.06
     åĸ
    -0.06
    ett
    -0.06
    shine
    -0.06
    POSITIVE LOGITS
    наÑĩ
    0.07
     Dich
    0.06
    addtogroup
    0.06
     SKIP
    0.06
    semblies
    0.06
    iscrim
    0.06
    ulin
    0.06
     Deposit
    0.06
     Beth
    0.06
    isd
    0.06
    Activations Density 0.002%

    No Known Activations