© 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. 5-LLAMASCOPE-RES-131K
    6. 126689
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and references to data manipulations or settings

    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
    uml
    -0.07
    @nate
    -0.07
    aster
    -0.07
    enda
    -0.06
     staging
    -0.06
    aylight
    -0.06
    .***.***
    -0.06
    ummer
    -0.06
     gauche
    -0.06
    -fontawesome
    -0.06
    POSITIVE LOGITS
    thers
    0.07
    assi
    0.06
    taÅŁ
    0.06
    éİ
    0.06
     Interracial
    0.06
     Tale
    0.06
    unma
    0.06
    uggle
    0.06
    Pont
    0.05
    Plain
    0.05
    Activations Density 0.094%

    No Known Activations