© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31471
    Prev
    Next
    INDEX
    Explanations

    elements related to visual content and product listings

    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
    ffen
    -0.08
     Redistributions
    -0.08
    @qq
    -0.07
    ityEngine
    -0.07
    icions
    -0.07
     STDCALL
    -0.07
    ccione
    -0.07
    ikk
    -0.07
    ttp
    -0.07
    úi
    -0.07
    POSITIVE LOGITS
     preview
    0.07
     details
    0.07
     detail
    0.07
     front
    0.06
     frontal
    0.06
     Detail
    0.06
     Front
    0.06
     model
    0.06
     image
    0.05
     view
    0.05
    Activations Density 0.004%

    No Known Activations