© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    terms related to financial policies and capital management

    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
    elder
    -0.08
    iglia
    -0.07
    itol
    -0.07
    strup
    -0.07
    EXP
    -0.06
    wig
    -0.06
    stalk
    -0.06
    ritten
    -0.06
    els
    -0.06
     Lif
    -0.06
    POSITIVE LOGITS
    PERT
    0.08
    activities
    0.07
    arness
    0.07
     decision
    0.07
    åĨ³
    0.07
     unreal
    0.06
     dose
    0.06
    avern
    0.06
     internals
    0.06
    /stdc
    0.06
    Activations Density 0.007%

    No Known Activations