© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40974
    Prev
    Next
    INDEX
    Explanations

    time durations in minutes

    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
    ï¸
    -0.07
    对æĸ¹
    -0.07
    еÑģÑı
    -0.07
     ìĿ´ëŁ¬
    -0.07
    odge
    -0.07
    è¦ļ
    -0.07
    çľĭè§ģ
    -0.06
    ربÙĬØ©
    -0.06
     IHttp
    -0.06
    ÙĤت
    -0.06
    POSITIVE LOGITS
     self
    0.06
     an
    0.06
     ca
    0.06
     a
    0.06
    rax
    0.06
    -self
    0.05
     studio
    0.05
     lots
    0.05
     with
    0.05
     multi
    0.05
    Activations Density 0.000%

    No Known Activations