© 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 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. 56204
    Prev
    Next
    INDEX
    Explanations

    financial expenditures and budgeting details

    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
    輸
    -0.06
    anner
    -0.06
    orian
    -0.06
    nger
    -0.06
    ani
    -0.06
    ľ
    -0.06
    gmt
    -0.06
    edii
    -0.05
    .simple
    -0.05
    esen
    -0.05
    POSITIVE LOGITS
     budget
    0.09
    Budget
    0.09
     Budget
    0.08
    budget
    0.08
    emey
    0.07
    -budget
    0.07
    _budget
    0.07
     ì¶ľìĹ°
    0.07
    irez
    0.07
    tical
    0.07
    Activations Density 0.008%

    No Known Activations