© 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. 82042
    Prev
    Next
    INDEX
    Explanations

    terms related to non-compliance or the absence of certain entitlements

    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
    EATURE
    -0.07
    å»
    -0.07
    ëģĶ
    -0.06
     buffering
    -0.06
    OLUMN
    -0.06
    amar
    -0.06
    .Actor
    -0.06
    ãĥªãĤ«
    -0.06
    _NC
    -0.06
    _parm
    -0.06
    POSITIVE LOGITS
    ace
    0.07
    ance
    0.07
    attendance
    0.07
    ACE
    0.06
     ace
    0.06
    é³¥
    0.06
    ãĥ¼ãĤ¹ãĥĪ
    0.06
    สà¸Ļ
    0.06
     attendance
    0.06
    atest
    0.06
    Activations Density 0.013%

    No Known Activations