© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 119792
    Prev
    Next
    INDEX
    Explanations

    structured programming or styling elements, particularly in CSS

    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
    ControlEvents
    -0.09
    eyse
    -0.09
    RIPT
    -0.08
    .googlecode
    -0.08
    BOOLE
    -0.08
    ooth
    -0.08
    HeaderCode
    -0.08
    LIK
    -0.07
    Äįel
    -0.07
     Ogre
    -0.07
    POSITIVE LOGITS
     censorship
    0.06
    avit
    0.06
    #/
    0.06
     kne
    0.06
    oton
    0.05
    .hr
    0.05
    é¦
    0.05
     https
    0.05
    974
    0.05
     Gerald
    0.05
    Activations Density 0.008%

    No Known Activations