© 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. 79796
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to theories, hypotheses, and analyses in social sciences and biology

    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
    keh
    -0.07
    dlg
    -0.06
    irs
    -0.06
    تد
    -0.06
    fty
    -0.06
    anou
    -0.06
    etu
    -0.06
    olatile
    -0.06
    annies
    -0.06
    obili
    -0.06
    POSITIVE LOGITS
     theory
    0.13
     approach
    0.13
     Approach
    0.11
     Theory
    0.10
     model
    0.10
    theory
    0.09
    appro
    0.09
    _appro
    0.09
    Theory
    0.08
     hypothesis
    0.08
    Activations Density 0.052%

    No Known Activations