© 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. 78035
    Prev
    Next
    INDEX
    Explanations

    possessive language indicating ownership or inclusion

    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
     Mond
    -0.07
     torn
    -0.06
     fellow
    -0.06
     pl
    -0.06
     ne
    -0.06
     mon
    -0.06
     fate
    -0.05
    ide
    -0.05
     places
    -0.05
    283
    -0.05
    POSITIVE LOGITS
    tesy
    0.08
    shal
    0.08
    ÙĤÙĬ
    0.08
    /REC
    0.08
    anax
    0.08
    propri
    0.07
    exclusive
    0.07
    loub
    0.07
    edef
    0.07
    ecure
    0.07
    Activations Density 0.023%

    No Known Activations