© 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. 9-LLAMASCOPE-RES-131K
    11. 98070
    Prev
    Next
    INDEX
    Explanations

    details related to publication dates and issues

    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
    ni
    -0.06
    zing
    -0.06
    ray
    -0.06
     lean
    -0.05
    竹
    -0.05
     ham
    -0.05
    ny
    -0.05
    chan
    -0.05
    åĦĢ
    -0.05
     evidence
    -0.05
    POSITIVE LOGITS
     rub
    0.08
     Rubin
    0.07
    agu
    0.07
    PFN
    0.07
    tabpanel
    0.07
    رÙĪØ´
    0.07
    ibase
    0.07
    aos
    0.07
    noop
    0.07
    wright
    0.06
    Activations Density 0.077%

    No Known Activations