© 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. 69596
    Prev
    Next
    INDEX
    Explanations

    challenges related to readability and accessibility in content

    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
    apl
    -0.06
     Quar
    -0.06
    phas
    -0.05
    xcf
    -0.05
    inputs
    -0.05
     Pee
    -0.05
    unger
    -0.05
     Po
    -0.05
     sensed
    -0.05
     Progress
    -0.05
    POSITIVE LOGITS
     leg
    0.09
     illeg
    0.08
    Courier
    0.08
    Leg
    0.08
     font
    0.08
     readability
    0.08
     Bolt
    0.08
     Courier
    0.07
     Legends
    0.07
    AMI
    0.07
    Activations Density 0.017%

    No Known Activations