© 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. 58264
    Prev
    Next
    INDEX
    Explanations

    elements related to clinical studies and research findings

    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
    zac
    -0.08
    aram
    -0.07
    onis
    -0.07
    ional
    -0.07
    ollen
    -0.06
    inz
    -0.06
    kest
    -0.06
    ker
    -0.06
    zen
    -0.06
     Dann
    -0.06
    POSITIVE LOGITS
    Ľå»º
    0.07
    isyon
    0.06
    )object
    0.06
    .SDK
    0.06
    gregar
    0.06
    νÏī
    0.06
    Mine
    0.06
    eel
    0.06
    imedia
    0.06
     ade
    0.06
    Activations Density 0.007%

    No Known Activations