© 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. 22-LLAMASCOPE-RES-131K
    11. 4037
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and participation in events

    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
    aine
    -0.06
    amer
    -0.06
    è¡
    -0.06
     FindObjectOfType
    -0.06
    use
    -0.05
     vents
    -0.05
    ists
    -0.05
    init
    -0.05
    tone
    -0.05
     cages
    -0.05
    POSITIVE LOGITS
    rchive
    0.07
    PageSize
    0.07
    andbox
    0.07
    voje
    0.07
    ousel
    0.07
     addCriterion
    0.07
    _imag
    0.07
    noinspection
    0.07
    vé
    0.07
    solete
    0.07
    Activations Density 0.001%

    No Known Activations