© 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. 104153
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and references

    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
    oretical
    -0.07
    BITS
    -0.06
    ol
    -0.06
    sek
    -0.06
    iare
    -0.06
    bits
    -0.05
     repeated
    -0.05
    awy
    -0.05
    ancestor
    -0.05
    lopen
    -0.05
    POSITIVE LOGITS
    BackingField
    0.08
    OffsetTable
    0.08
    FunctionFlags
    0.07
    AINED
    0.07
    ospace
    0.07
     "";č↵
    0.07
     Nylon
    0.07
    eÅŁ
    0.07
    .dex
    0.07
    óc
    0.07
    Activations Density 0.001%

    No Known Activations