© 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. 1986
    Prev
    Next
    INDEX
    Explanations

    the presence of the token "en" in various contexts, likely indicating references to entities or items, particularly in technical or formal descriptions

    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
    akespeare
    -0.06
    adh
    -0.06
    unity
    -0.06
    ewis
    -0.06
     Phys
    -0.06
    onde
    -0.06
    clean
    -0.06
    _SAFE
    -0.05
    esel
    -0.05
    åħ
    -0.05
    POSITIVE LOGITS
    QUIRE
    0.07
    ibold
    0.07
    itionally
    0.07
    antro
    0.07
    ربÙĩ
    0.07
    δÏģο
    0.07
    nodoc
    0.07
    quired
    0.07
    atty
    0.06
    .hh
    0.06
    Activations Density 0.013%

    No Known Activations