© 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. 77600
    Prev
    Next
    INDEX
    Explanations

    inquiries about preferences and choices

    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
    梯
    -0.07
     FactoryGirl
    -0.06
    रण
    -0.06
    ØŃÙħ
    -0.06
     FactoryBot
    -0.06
    ÑĤаб
    -0.06
    IRC
    -0.06
    ÎŃν
    -0.06
    Animating
    -0.06
    ãĥ¼ãĥį
    -0.06
    POSITIVE LOGITS
    837
    0.07
    qa
    0.07
     nues
    0.07
    bm
    0.06
    aut
    0.06
    ãĥ¼ãĥ©
    0.06
    parm
    0.06
    raki
    0.06
    alim
    0.06
     extinct
    0.06
    Activations Density 0.005%

    No Known Activations