© 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. 123955
    Prev
    Next
    INDEX
    Explanations

    phrases indicating procedures or steps that need to be followed

    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
    izza
    -0.07
    smarty
    -0.07
    enk
    -0.07
    .Networking
    -0.06
    ale
    -0.06
    Ìģ
    -0.06
    outh
    -0.06
     contr
    -0.06
    ERE
    -0.06
    bai
    -0.06
    POSITIVE LOGITS
    drs
    0.07
    á»įng
    0.07
    oze
    0.07
    ìĽ
    0.07
    iefs
    0.07
    ĽĦ
    0.07
    ikan
    0.06
    ีà¸Ĭ
    0.06
    unch
    0.06
    IFS
    0.06
    Activations Density 0.002%

    No Known Activations