© 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. 15-LLAMASCOPE-RES-131K
    11. 1370
    Prev
    Next
    INDEX
    Explanations

    narratives centered on personal life experiences and ethical dilemmas

    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
    quit
    -0.07
    rr
    -0.07
    ucer
    -0.06
    æĬĺ
    -0.06
    ungan
    -0.06
    -0.06
    hdl
    -0.06
     Gad
    -0.06
    çĶ·
    -0.06
     put
    -0.06
    POSITIVE LOGITS
    ussy
    0.07
    ̣
    0.06
    ::$_
    0.06
    üst
    0.06
    TriState
    0.06
     cazzo
    0.06
    chia
    0.06
    _shortcode
    0.06
    æīķ
    0.06
    pyx
    0.06
    Activations Density 0.012%

    No Known Activations