© 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. 15-LLAMASCOPE-RES-131K
    11. 87602
    Prev
    Next
    INDEX
    Explanations

    specific names or entities related to news events or awards

    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
    ãĤ¼
    -0.07
    ahoma
    -0.07
    /ts
    -0.07
    erland
    -0.07
    amu
    -0.07
     Barnett
    -0.07
    &o
    -0.07
    LEC
    -0.06
     Blitz
    -0.06
    uby
    -0.06
    POSITIVE LOGITS
    ugin
    0.06
     Slow
    0.06
    Slow
    0.06
    threads
    0.06
    self
    0.06
     Spar
    0.06
    agnet
    0.06
     Achilles
    0.06
     slow
    0.05
    761
    0.05
    Activations Density 0.000%

    No Known Activations