© 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. 39000
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviews and feedback

    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
    qli
    -0.08
    azi
    -0.07
     Mun
    -0.06
    pei
    -0.06
    iper
    -0.06
    ãĥ³ãĤ¿
    -0.06
    ftware
    -0.06
     ç¿
    -0.06
    mund
    -0.06
    phin
    -0.06
    POSITIVE LOGITS
    asca
    0.07
    برÛĮ
    0.07
    chter
    0.06
    illac
    0.06
    _APPS
    0.06
    ynes
    0.06
    erea
    0.06
    .accounts
    0.06
     Alg
    0.06
     Abyss
    0.06
    Activations Density 0.007%

    No Known Activations