© 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. 72578
    Prev
    Next
    INDEX
    Explanations

    instances of "giving," "posting," or "asking" activities

    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
     vapor
    -0.06
    añ
    -0.06
    ĵį
    -0.06
    CONTEXT
    -0.06
    827
    -0.06
    лем
    -0.06
    ising
    -0.06
    ect
    -0.05
    alink
    -0.05
    avery
    -0.05
    POSITIVE LOGITS
    andle
    0.07
    onse
    0.07
    éĺ³åŁİ
    0.07
    ths
    0.07
     Tip
    0.06
    astle
    0.06
    ipi
    0.06
     Forg
    0.06
    velte
    0.06
    unde
    0.06
    Activations Density 0.041%

    No Known Activations