© 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. 15846
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating relation and description

    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
    umb
    -0.06
    LL
    -0.06
    avers
    -0.06
    esimal
    -0.06
    heels
    -0.06
    cba
    -0.06
    vl
    -0.06
     nackt
    -0.05
    901
    -0.05
     Gia
    -0.05
    POSITIVE LOGITS
    _tac
    0.07
    etin
    0.07
     Baum
    0.06
    .Constant
    0.06
    artz
    0.06
    resa
    0.06
     ancor
    0.06
     myš
    0.06
    .LA
    0.06
    /device
    0.06
    Activations Density 0.025%

    No Known Activations