© 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. 95098
    Prev
    Next
    INDEX
    Explanations

    relationships between social equity and policies or practices aimed at improving financial sustainability

    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
    iaux
    -0.08
    ÌĨ
    -0.07
    upd
    -0.07
    ãĥ³ãĤº
    -0.07
    _processors
    -0.07
    _SPELL
    -0.06
    iec
    -0.06
     NgÃły
    -0.06
    imity
    -0.06
    ModifiedDate
    -0.06
    POSITIVE LOGITS
     legislation
    0.08
     funding
    0.07
     policy
    0.07
     implementation
    0.07
     execution
    0.07
    haps
    0.06
     hardware
    0.06
     programs
    0.06
     individual
    0.06
    irmware
    0.06
    Activations Density 0.022%

    No Known Activations