© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60396
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and elements related to coding frameworks

    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
     Harden
    -0.07
    ILE
    -0.06
    çĹĩ
    -0.06
     Gale
    -0.06
    ukkan
    -0.06
    ugo
    -0.06
    orton
    -0.06
    egra
    -0.06
     Sexe
    -0.06
    еж
    -0.06
    POSITIVE LOGITS
    ãģ¡ãĤĩ
    0.07
     Gerard
    0.06
    oup
    0.06
    increments
    0.06
    omu
    0.06
    taÅŁ
    0.06
     Times
    0.06
    ä¸
    0.06
    701
    0.05
     ratings
    0.05
    Activations Density 0.012%

    No Known Activations