© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74510
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and elements of class structure

    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
     imm
    -0.07
     Fred
    -0.06
     Bes
    -0.06
    ripe
    -0.06
     sharp
    -0.06
     dist
    -0.05
     sed
    -0.05
    :
    -0.05
     fe
    -0.05
    ess
    -0.05
    POSITIVE LOGITS
    (savedInstanceState
    0.10
     ngOnInit
    0.08
     onCreate
    0.08
    .Override
    0.08
    ViewInit
    0.07
     setContentView
    0.07
    Transparent
    0.07
     ninh
    0.07
    è³Ģ
    0.07
     initComponents
    0.07
    Activations Density 0.002%

    No Known Activations