© 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. 28552
    Prev
    Next
    INDEX
    Explanations

    content related to educational programs and improvement initiatives

    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
    arken
    -0.07
    elter
    -0.07
    ä½ĵ
    -0.07
    Slash
    -0.06
    NU
    -0.06
    aram
    -0.06
    ITHER
    -0.06
    .RegisterType
    -0.06
     Erg
    -0.06
    ocup
    -0.06
    POSITIVE LOGITS
     Program
    0.08
     program
    0.08
     programme
    0.07
     Programme
    0.07
    program
    0.07
    essim
    0.07
     programu
    0.06
     intervention
    0.06
     intervened
    0.06
    ej
    0.06
    Activations Density 0.048%

    No Known Activations