© 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. 9-LLAMASCOPE-RES-131K
    11. 95365
    Prev
    Next
    INDEX
    Explanations

    legal references and citations

    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
    nger
    -0.07
    IntArray
    -0.07
    ije
    -0.07
    ongs
    -0.06
    ãĥ¼ãĥŃ
    -0.06
    ron
    -0.06
    _FALL
    -0.06
    er
    -0.06
     Vern
    -0.06
     getVersion
    -0.06
    POSITIVE LOGITS
     Clayton
    0.07
    ĵĺ
    0.06
    rites
    0.06
    ensi
    0.06
     Consort
    0.06
    sgi
    0.06
     Rencontres
    0.06
    ζη
    0.06
    achu
    0.06
    /vue
    0.06
    Activations Density 0.012%

    No Known Activations