© 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. 125447
    Prev
    Next
    INDEX
    Explanations

    references to economic and political institutions, particularly those related to power dynamics and international relations

    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
    avig
    -0.07
    éĿ©åij½
    -0.07
    erez
    -0.07
     Guerrero
    -0.06
     Boo
    -0.06
    EMPLARY
    -0.06
    bourne
    -0.06
    ãģĨãģ¡
    -0.06
    orea
    -0.06
     Guerr
    -0.06
    POSITIVE LOGITS
     recent
    0.07
    ouch
    0.07
    icher
    0.07
    myp
    0.06
    tor
    0.06
    ä¸ĢçĤ¹
    0.06
    trand
    0.06
    ¯ÃĤ
    0.06
    _BOUND
    0.06
    pus
    0.06
    Activations Density 0.059%

    No Known Activations