© 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. 62641
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance or consistency of statements

    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
    оз
    -0.06
    Stamp
    -0.06
     wedge
    -0.06
    zan
    -0.06
    ith
    -0.06
     поÑĩ
    -0.06
    BITS
    -0.06
     (__
    -0.06
    kok
    -0.06
     Antwort
    -0.06
    POSITIVE LOGITS
     this
    0.09
     unlike
    0.08
     these
    0.08
    rál
    0.07
     since
    0.07
    this
    0.07
    ,this
    0.07
    utar
    0.07
    ablo
    0.07
     Unlike
    0.07
    Activations Density 0.029%

    No Known Activations