© 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. 59761
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and distribution rights

    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
    omal
    -0.06
    idea
    -0.06
    ucks
    -0.06
    zie
    -0.06
     lick
    -0.06
    erea
    -0.06
    .Prot
    -0.06
    gn
    -0.06
    /home
    -0.05
    amy
    -0.05
    POSITIVE LOGITS
    antro
    0.08
    icÃŃ
    0.07
    ulos
    0.07
    etten
    0.07
    #echo
    0.07
    á»ĭ
    0.07
    ãĥ³ãĤ¹
    0.07
    ulur
    0.07
    eward
    0.07
    olo
    0.07
    Activations Density 0.001%

    No Known Activations