© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127694
    Prev
    Next
    INDEX
    Explanations

    references to transactions or modifications involving physical or abstract objects

    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
     memoir
    -0.08
     autobiography
    -0.07
     Alg
    -0.06
    }elseif
    -0.06
    STYPE
    -0.06
     Watt
    -0.06
     mi
    -0.05
    ÑĬ
    -0.05
    gor
    -0.05
     Bench
    -0.05
    POSITIVE LOGITS
     its
    0.08
    chl
    0.08
    Ùħد
    0.08
    enthal
    0.08
    zia
    0.08
    //{{
    0.08
     nó
    0.07
    bard
    0.07
     dziew
    0.07
    enumerator
    0.07
    Activations Density 0.028%

    No Known Activations