© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55549
    Prev
    Next
    INDEX
    Explanations

    possessive forms or contractions

    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
    upp
    -0.08
    .pix
    -0.07
    esin
    -0.07
    ’Ñıз
    -0.07
    Ø®ÙĪاÙĨ
    -0.07
    geç
    -0.06
     sami
    -0.06
    باز
    -0.06
    åħĪçĶŁ
    -0.06
    igos
    -0.06
    POSITIVE LOGITS
     sake
    0.07
     alike
    0.07
    quir
    0.07
    edn
    0.06
     worth
    0.06
    aston
    0.06
    uggested
    0.06
    .Transactional
    0.06
    sole
    0.06
    alles
    0.06
    Activations Density 0.105%

    No Known Activations