© 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. 61298
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical accuracy and verification

    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
    376
    -0.07
     rhet
    -0.06
     Arguments
    -0.06
    λÏİ
    -0.05
    Arguments
    -0.05
    æ´ģ
    -0.05
     Flores
    -0.05
    FAILURE
    -0.05
    ulos
    -0.05
    θη
    -0.05
    POSITIVE LOGITS
     accuracy
    0.21
     accurate
    0.19
    accuracy
    0.19
     Accuracy
    0.18
    accur
    0.18
    Accuracy
    0.16
     accur
    0.16
     inaccurate
    0.14
     correctness
    0.14
     correct
    0.14
    Activations Density 0.063%

    No Known Activations