© 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. 88092
    Prev
    Next
    INDEX
    Explanations

    historical events and transitions related to religious or political changes

    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
    zend
    -0.08
    zer
    -0.08
    Łèĥ½
    -0.07
    .Sdk
    -0.07
    ghan
    -0.07
    isclosed
    -0.07
    rose
    -0.07
    izr
    -0.07
    aska
    -0.07
    ecs
    -0.07
    POSITIVE LOGITS
     reform
    0.09
     reforms
    0.08
     Protest
    0.07
     Reform
    0.07
     Hex
    0.06
     charismatic
    0.06
     Calvin
    0.06
     Barrel
    0.06
    ensions
    0.06
     syn
    0.06
    Activations Density 0.003%

    No Known Activations