© 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. 74144
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions or monetary values

    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
     burial
    -0.06
    ÑĢеÑī
    -0.06
     unm
    -0.06
     Pent
    -0.06
     module
    -0.06
    pell
    -0.06
     Roose
    -0.06
    ánt
    -0.05
     Perf
    -0.05
     state
    -0.05
    POSITIVE LOGITS
    oslav
    0.08
    .decorate
    0.07
    ucher
    0.07
    taÅŁ
    0.06
    leich
    0.06
     Wich
    0.06
    _cou
    0.06
    entlich
    0.06
    ucci
    0.06
    _GENER
    0.06
    Activations Density 0.001%

    No Known Activations