© 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. 105828
    Prev
    Next
    INDEX
    Explanations

    instructions related to completing an application

    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
    unate
    -0.07
    avors
    -0.07
    icone
    -0.06
    ovol
    -0.06
     Duel
    -0.06
    ruz
    -0.06
    kü
    -0.06
    /rem
    -0.06
    elen
    -0.06
    unger
    -0.06
    POSITIVE LOGITS
     fields
    0.10
    _fields
    0.08
    -fields
    0.08
     filled
    0.08
    fields
    0.08
     Fields
    0.08
     Completion
    0.07
    Fields
    0.07
    .fill
    0.07
    .Completed
    0.07
    Activations Density 0.005%

    No Known Activations