© 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. 17-LLAMASCOPE-RES-131K
    11. 29575
    Prev
    Next
    INDEX
    Explanations

    connecting words and conjunctions that link phrases or ideas together in a text

    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
    asma
    -0.07
    dll
    -0.07
    moire
    -0.07
    ạm
    -0.07
    launcher
    -0.06
    icari
    -0.06
    lator
    -0.06
    onde
    -0.06
    ovit
    -0.06
    lify
    -0.06
    POSITIVE LOGITS
     century
    0.08
    ãĥ¼ãĤ¹ãĥĪ
    0.06
     fout
    0.06
    енÑĤи
    0.06
    avanaugh
    0.06
    жд
    0.06
    Forgery
    0.06
    ÃŃd
    0.06
     Imag
    0.06
     upper
    0.06
    Activations Density 0.008%

    No Known Activations