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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57587
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and functions

    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
    yles
    -0.07
    achel
    -0.07
    epar
    -0.07
    aten
    -0.06
    ervas
    -0.06
    iec
    -0.06
    hatt
    -0.06
    éļĨ
    -0.06
     Charlottesville
    -0.06
    ($(
    -0.06
    POSITIVE LOGITS
     Zend
    0.08
    nesc
    0.07
     PHP
    0.07
    Zend
    0.07
    =array
    0.07
    ,array
    0.07
    |array
    0.07
     array
    0.07
    ENGINE
    0.07
    ZF
    0.07
    Activations Density 0.121%

    No Known Activations