© 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. 9-LLAMASCOPE-RES-131K
    11. 97128
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to modeling and constraints

    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
    iards
    -0.08
    rooms
    -0.08
    others
    -0.07
    alama
    -0.07
    ÄĽtÃŃ
    -0.07
    usu
    -0.07
    oÄį
    -0.07
    .System
    -0.07
    ousel
    -0.07
    iard
    -0.07
    POSITIVE LOGITS
    odore
    0.08
    WEEN
    0.07
    ullah
    0.07
    .GroupLayout
    0.06
    oret
    0.06
    oriously
    0.06
     Strict
    0.06
     Garten
    0.06
    erdale
    0.06
    atchewan
    0.06
    Activations Density 2.799%

    No Known Activations