© 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. 79417
    Prev
    Next
    INDEX
    Explanations

    elements of code or programming instructions

    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
     Davidson
    -0.06
    396
    -0.06
    764
    -0.06
     repro
    -0.06
     tear
    -0.06
     bin
    -0.06
    atte
    -0.06
    ductive
    -0.06
     bais
    -0.06
    as
    -0.05
    POSITIVE LOGITS
     startActivity
    0.09
    	startActivity
    0.09
    StackNavigator
    0.08
    Qualifier
    0.07
    eger
    0.07
    γα
    0.07
    scoped
    0.07
     Lod
    0.07
    awei
    0.07
    .putExtra
    0.07
    Activations Density 0.002%

    No Known Activations