© 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. 74615
    Prev
    Next
    INDEX
    Explanations

    references to past roles or previous states of being

    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
    ami
    -0.06
    aware
    -0.06
    opp
    -0.06
    缮åīį
    -0.06
    yy
    -0.06
    âĢĮاÙĨ
    -0.06
    ırak
    -0.06
    ener
    -0.06
    ra
    -0.06
    ByExample
    -0.06
    POSITIVE LOGITS
    /current
    0.14
    /new
    0.10
    /original
    0.09
    yme
    0.08
     glory
    0.08
     Yugoslavia
    0.08
    lies
    0.08
    rier
    0.08
    most
    0.08
    mente
    0.08
    Activations Density 0.014%

    No Known Activations