© 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. 15598
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to performance metrics or financial analysis

    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
    scopes
    -0.06
    kers
    -0.06
     une
    -0.06
    634
    -0.06
    393
    -0.06
    enia
    -0.06
    eya
    -0.06
     qualify
    -0.06
    illet
    -0.06
    iler
    -0.05
    POSITIVE LOGITS
    imdi
    0.07
     olun
    0.07
    uesta
    0.07
     trải
    0.07
    çĶĺ
    0.07
    าà¸
    0.07
    .dp
    0.07
     oto
    0.07
    ιÏĥÏĦο
    0.07
     Dữ
    0.07
    Activations Density 0.013%

    No Known Activations