© 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. 41814
    Prev
    Next
    INDEX
    Explanations

    phrases related to constraints and limitations

    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
     dh
    -0.07
     whenever
    -0.07
    Rendering
    -0.06
     wherever
    -0.06
    üss
    -0.06
    readcr
    -0.06
    DH
    -0.06
    sek
    -0.06
     cas
    -0.06
    odef
    -0.06
    POSITIVE LOGITS
     anymore
    0.12
    ä»»ä½ķ
    0.11
     žádné
    0.10
    à¹ĥà¸Ķ
    0.10
     вообÑīе
    0.09
     nor
    0.09
     neither
    0.09
     altogether
    0.08
    nor
    0.08
     any
    0.08
    Activations Density 0.056%

    No Known Activations