© 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. 106136
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to computational methods and algorithms in data estimation

    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
    weis
    -0.08
    umd
    -0.07
    ycz
    -0.07
     Predictor
    -0.07
    orm
    -0.07
    agenta
    -0.07
    emem
    -0.07
     predictive
    -0.06
     cáºŃn
    -0.06
    γκα
    -0.06
    POSITIVE LOGITS
     reconstruction
    0.07
    odable
    0.07
     tom
    0.07
    ÑĩиÑĤ
    0.06
     inversion
    0.06
    unwrap
    0.06
     methods
    0.06
    203
    0.06
     principal
    0.06
     reconstruct
    0.06
    Activations Density 0.198%

    No Known Activations