© 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. 15-LLAMASCOPE-RES-131K
    6. 90632
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to statistical estimation and properties

    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
    .fp
    -0.07
    aul
    -0.07
    Fault
    -0.07
    ANJI
    -0.07
    fault
    -0.07
    icular
    -0.07
    atus
    -0.07
    ubbo
    -0.07
    /stretch
    -0.07
    makt
    -0.07
    POSITIVE LOGITS
    ime
    0.06
     excess
    0.06
    å®
    0.06
    öl
    0.06
    oric
    0.06
     departure
    0.06
    					↵					↵
    0.06
    _stderr
    0.05
    abl
    0.05
    .define
    0.05
    Activations Density 0.051%

    No Known Activations