© 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. 57810
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to defining and describing processes or methods

    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
    LEC
    -0.07
    hw
    -0.06
    ound
    -0.06
    irm
    -0.06
     Bullet
    -0.06
     tid
    -0.06
    ayas
    -0.06
    rade
    -0.05
    tar
    -0.05
    ool
    -0.05
    POSITIVE LOGITS
     Escape
    0.08
     souÄįasné
    0.07
    ovit
    0.07
    .rawValue
    0.07
    orian
    0.07
    Escape
    0.07
    ampa
    0.07
    /Edit
    0.07
    	Copyright
    0.07
    escaping
    0.07
    Activations Density 0.002%

    No Known Activations