© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 62209
    Prev
    Next
    INDEX
    Explanations

    terminologies related to government and finance

    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
    _mE
    -0.08
    uctions
    -0.08
    ANNEL
    -0.07
    rale
    -0.07
    ROKE
    -0.07
    otal
    -0.07
    _Lean
    -0.07
    usercontent
    -0.07
    iquid
    -0.07
    CppType
    -0.07
    POSITIVE LOGITS
     Department
    0.08
     department
    0.07
     ministry
    0.07
     wing
    0.06
     Dept
    0.06
     eas
    0.06
     dept
    0.06
    afort
    0.06
     Ministry
    0.06
     estimated
    0.06
    Activations Density 0.025%

    No Known Activations