© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126366
    Prev
    Next
    INDEX
    Explanations

    references to grammar and grammatical concepts

    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
    legate
    -0.08
    ãĤ§
    -0.08
    aes
    -0.07
    yor
    -0.07
    bies
    -0.07
    éry
    -0.07
    ̣
    -0.07
    aris
    -0.07
    velt
    -0.06
    salt
    -0.06
    POSITIVE LOGITS
    atical
    0.09
    atically
    0.07
    weet
    0.07
    ayne
    0.07
    ical
    0.07
    oidal
    0.07
     dÄ±ÅŁÄ±
    0.06
    idge
    0.06
    arians
    0.06
    azed
    0.06
    Activations Density 0.005%

    No Known Activations