© 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. 92983
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or alternatives in recommendations

    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
    IPA
    -0.07
    lev
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    нен
    -0.06
    iyah
    -0.06
    istani
    -0.06
    umas
    -0.06
    ĶĦ
    -0.06
    arking
    -0.06
    allet
    -0.06
    POSITIVE LOGITS
    vig
    0.07
     ØŃسب
    0.07
     equival
    0.07
     же
    0.06
    ç«ĭãģ¦
    0.06
     ì¢Ģ
    0.06
    ignal
    0.06
     conven
    0.06
    chap
    0.06
    çŃĴ
    0.06
    Activations Density 0.008%

    No Known Activations