© 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. 107045
    Prev
    Next
    INDEX
    Explanations

    programming constructs and performance-related language features

    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
    eyse
    -0.09
    êm
    -0.07
    assis
    -0.07
    amente
    -0.06
    rientation
    -0.06
    ÅĻeh
    -0.06
    vÄĽÅĻ
    -0.06
    _refl
    -0.06
    omid
    -0.06
    trie
    -0.06
    POSITIVE LOGITS
     loop
    0.13
     loops
    0.13
    _loop
    0.12
    -loop
    0.11
    loop
    0.11
     Loop
    0.10
    loops
    0.10
    Loop
    0.10
    循
    0.09
     looping
    0.09
    Activations Density 0.036%

    No Known Activations