© 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. 29528
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements in HTML and React code

    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
    isoft
    -0.08
    iggs
    -0.08
     xrange
    -0.08
     xbmc
    -0.08
    iage
    -0.07
     initWithNibName
    -0.07
    ajar
    -0.07
    opis
    -0.07
     Kinect
    -0.07
    ạch
    -0.07
    POSITIVE LOGITS
    202
    0.06
    Hp
    0.06
     Baby
    0.06
    کاÙĨ
    0.06
     Tik
    0.05
     Hp
    0.05
     Passport
    0.05
     fet
    0.05
    æŀ¶
    0.05
     Ek
    0.05
    Activations Density 0.129%

    No Known Activations