© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118300
    Prev
    Next
    INDEX
    Explanations

    instances of the word "form" and variations of it

    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
    pai
    -0.08
    kke
    -0.07
    aska
    -0.07
    veis
    -0.07
    ãĥĻãĥ«
    -0.07
     Directions
    -0.07
    ittal
    -0.07
    аж
    -0.06
    aty
    -0.06
    ава
    -0.06
    POSITIVE LOGITS
    ulating
    0.09
     teams
    0.08
     partnerships
    0.08
    ulates
    0.07
     habit
    0.07
     basis
    0.07
     formation
    0.07
    teams
    0.07
     habits
    0.07
    ulators
    0.06
    Activations Density 0.019%

    No Known Activations