© 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. 3402
    Prev
    Next
    INDEX
    Explanations

    references to specific news outlets and media organizations

    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
    çī
    -0.07
    BOSE
    -0.07
    ogan
    -0.07
    iban
    -0.06
    _PROGRAM
    -0.06
    ather
    -0.06
    ocaust
    -0.06
    ÏĨι
    -0.06
    ertext
    -0.06
    ppo
    -0.06
    POSITIVE LOGITS
     Bram
    0.07
    e
    0.07
     Wesley
    0.06
    a
    0.06
    iÄĩ
    0.06
    sah
    0.06
    æĮ¯
    0.06
     Amir
    0.05
    ãģĭãģ®
    0.05
    dal
    0.05
    Activations Density 0.001%

    No Known Activations