© 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. 83579
    Prev
    Next
    INDEX
    Explanations

    indications of code generation and file metadata

    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
    tr
    -0.06
    anz
    -0.06
    -es
    -0.06
    eck
    -0.06
     dem
    -0.06
    oste
    -0.06
    trie
    -0.06
    ,
    -0.06
    steen
    -0.06
    ched
    -0.05
    POSITIVE LOGITS
    .generated
    0.10
    Generated
    0.09
    pyx
    0.08
    generated
    0.07
     èĩªåĬ¨çĶŁæĪIJ
    0.07
    .documentation
    0.07
    edException
    0.07
    AXB
    0.07
    Desk
    0.07
    Multiplicity
    0.07
    Activations Density 0.002%

    No Known Activations