© 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. 9-LLAMASCOPE-RES-131K
    11. 94496
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering or mechanics

    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
    odzi
    -0.07
    BootTest
    -0.07
    ãĥ¼ãĥŃ
    -0.07
    ngr
    -0.07
    raki
    -0.07
    å·»
    -0.07
    _growth
    -0.07
     NUIT
    -0.07
    emann
    -0.07
    RTOS
    -0.07
    POSITIVE LOGITS
      č↵č↵
    0.06
    εÏį
    0.06
     convention
    0.06
     disp
    0.06
    up
    0.05
    ogen
    0.05
    anj
    0.05
    ffen
    0.05
     sol
    0.05
    fmt
    0.05
    Activations Density 0.084%

    No Known Activations