© 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 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. 9-LLAMASCOPE-RES-131K
    11. 97105
    Prev
    Next
    INDEX
    Explanations

    terms related to policy advocacy and oversight

    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
    riere
    -0.09
    .usermodel
    -0.07
    bero
    -0.07
    .scalablytyped
    -0.07
    rière
    -0.07
     everybody
    -0.06
    rious
    -0.06
     Denn
    -0.06
    ieri
    -0.06
    VERTISE
    -0.06
    POSITIVE LOGITS
    yor
    0.07
    ç©į
    0.07
    ãĥ©ãĤ¤ãĥĪ
    0.07
    æĪ¿å±ĭ
    0.07
    <?↵
    0.06
    748
    0.06
    ãĤ¤ãĥ³ãĥĪ
    0.06
    646
    0.06
    662
    0.06
     selv
    0.06
    Activations Density 0.026%

    No Known Activations