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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 85797
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of starting or beginning something

    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
    گاÙĩ
    -0.09
    fds
    -0.08
    agra
    -0.08
    èĪĹ
    -0.08
    .sax
    -0.08
    INCLUDED
    -0.08
    -alist
    -0.08
    ARNING
    -0.08
     dosy
    -0.08
    saldo
    -0.08
    POSITIVE LOGITS
     to
    0.12
    1
    0.08
    2
    0.08
    to
    0.07
    ↵
    0.07
    us
    0.07
    L
    0.06
    t
    0.06
    y
    0.06
    ly
    0.06
    Activations Density 0.025%

    No Known Activations