© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126636
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quotations or references to speech

    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
     Clayton
    -0.07
    ignon
    -0.06
    unden
    -0.06
    imd
    -0.06
    owell
    -0.06
     Ashe
    -0.06
    emos
    -0.06
    ierten
    -0.06
    ati
    -0.06
     ÑģоÑģÑĤав
    -0.06
    POSITIVE LOGITS
    legate
    0.07
    265
    0.07
    ARAM
    0.07
    tg
    0.06
    269
    0.06
    447
    0.06
     xsi
    0.06
    anik
    0.06
    277
    0.06
    ãģĮãģĦ
    0.06
    Activations Density 0.007%

    No Known Activations