© 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. 17-LLAMASCOPE-RES-131K
    6. 57841
    Prev
    Next
    INDEX
    Explanations

    less-than and greater-than symbols along with related tags or special characters commonly used in coding or markup languages

    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
    nie
    -0.07
    emale
    -0.07
    iaux
    -0.06
    peria
    -0.06
     Tenn
    -0.06
    олоÑĤ
    -0.06
    nier
    -0.06
    .gg
    -0.06
    ardless
    -0.06
    FRING
    -0.06
    POSITIVE LOGITS
     ActiveForm
    0.07
    Ñı
    0.06
    itter
    0.06
    θεÏģ
    0.06
    ound
    0.06
    اض
    0.06
     Franti
    0.06
    Lean
    0.06
    é½
    0.06
    reen
    0.05
    Activations Density 0.000%

    No Known Activations