© 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 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. 77186
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their attributes within the text

    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
    é¼ł
    -0.07
    csr
    -0.07
     ferr
    -0.07
    //{{
    -0.06
    _simps
    -0.06
    letcher
    -0.06
     undert
    -0.06
    å¾ħ
    -0.06
    HeaderValue
    -0.06
    çIJ´
    -0.06
    POSITIVE LOGITS
     Daly
    0.07
     Crist
    0.06
    oken
    0.06
    asename
    0.06
     discharge
    0.06
    usi
    0.06
     county
    0.06
     Kraj
    0.06
     Äijó
    0.06
    alaxy
    0.06
    Activations Density 0.002%

    No Known Activations