© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 62938
    Prev
    Next
    INDEX
    Explanations

    terms related to the measurement and identification of economic factors

    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
    ouri
    -0.07
    à¤Ĺर
    -0.06
    aeper
    -0.06
    _ANY
    -0.06
     deeper
    -0.06
     att
    -0.06
    icros
    -0.06
     ante
    -0.06
    .Platform
    -0.06
    -Sah
    -0.06
    POSITIVE LOGITS
     easy
    0.14
    easy
    0.13
     easier
    0.13
     straightforward
    0.13
     fácil
    0.12
     relatively
    0.12
     easily
    0.11
    æĺĵ
    0.11
     dá»ħ
    0.11
    容æĺĵ
    0.11
    Activations Density 0.059%

    No Known Activations