© 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 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. 9-LLAMASCOPE-RES-131K
    11. 97216
    Prev
    Next
    INDEX
    Explanations

    coding-related assertions and function definitions

    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
    annis
    -0.07
    upa
    -0.06
    ìĨį
    -0.06
     ìķĦëĭ
    -0.06
    ente
    -0.05
     åİ
    -0.05
     Gerr
    -0.05
    amina
    -0.05
     genetically
    -0.05
     Initial
    -0.05
    POSITIVE LOGITS
    \L
    0.07
    οι
    0.07
    LOCKS
    0.07
    ãĥķãĤ
    0.06
    ABEL
    0.06
    sole
    0.06
     useClass
    0.06
    IZER
    0.06
    arna
    0.06
    ADOR
    0.06
    Activations Density 0.086%

    No Known Activations