© 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. 92868
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" in various contexts

    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
    cky
    -0.08
    c
    -0.08
    le
    -0.08
    odore
    -0.07
    lu
    -0.07
    j
    -0.07
    b
    -0.07
    أ
    -0.07
    h
    -0.07
    st
    -0.07
    POSITIVE LOGITS
    rror
    0.08
     href
    0.08
     partir
    0.07
    EUR
    0.07
    terior
    0.07
     través
    0.07
    .k
    0.06
    sembly
    0.06
    esk
    0.06
    etten
    0.06
    Activations Density 0.078%

    No Known Activations