© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103126
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate preparation or readiness for an event

    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
    ayet
    -0.07
    ayi
    -0.06
    zim
    -0.06
     cig
    -0.06
     man
    -0.06
     exactly
    -0.06
     itself
    -0.05
     many
    -0.05
    ostel
    -0.05
    IME
    -0.05
    POSITIVE LOGITS
    ichel
    0.07
    ÅĽci
    0.07
    uger
    0.07
    izen
    0.07
    --------------------------------------------------------------------------↵
    0.07
     molec
    0.07
    ingly
    0.06
    ÚĨار
    0.06
    utan
    0.06
    ίÏīν
    0.06
    Activations Density 0.006%

    No Known Activations