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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 121277
    Prev
    Next
    INDEX
    Explanations

    terms related to aquatic insects and their life cycles

    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
    agues
    -0.07
    ensen
    -0.06
    AINER
    -0.06
    stab
    -0.06
    pur
    -0.06
    ettes
    -0.05
     rare
    -0.05
     atol
    -0.05
     inflamm
    -0.05
    rets
    -0.05
    POSITIVE LOGITS
    -*-
    0.08
    spent
    0.07
     заклад
    0.07
     adults
    0.07
    FromBody
    0.07
     Ấ
    0.07
    彦
    0.07
     spends
    0.06
     adult
    0.06
     Metallic
    0.06
    Activations Density 0.008%

    No Known Activations