© 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. 82010
    Prev
    Next
    INDEX
    Explanations

    instances of the page referencing a specific person's name

    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
    pread
    -0.08
    rior
    -0.08
    ÄĻż
    -0.08
     Ñģклад
    -0.07
    rente
    -0.07
    kiem
    -0.07
    isto
    -0.07
    ık
    -0.07
    unsch
    -0.07
    ded
    -0.07
    POSITIVE LOGITS
    0.06
     Cong
    0.06
    ↵
    0.05
     Trot
    0.05
    Cong
    0.05
     Tut
    0.05
     pe
    0.05
     whose
    0.05
     IP
    0.05
    -opacity
    0.05
    Activations Density 0.000%

    No Known Activations