© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "more" indicating an emphasis on quantity or additional information

    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
    10
    -0.08
     atleast
    -0.07
    1
    -0.07
    3
    -0.06
    7
    -0.06
    11
    -0.06
    01
    -0.06
     wherever
    -0.06
    5
    -0.06
     pages
    -0.06
    POSITIVE LOGITS
    eyJ
    0.08
    ANJI
    0.08
    ENSOR
    0.08
    $MESS
    0.07
    ajas
    0.07
    .glide
    0.07
     addCriterion
    0.07
    edReader
    0.07
    rawer
    0.07
    èĥ¶
    0.07
    Activations Density 0.027%

    No Known Activations