© 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. 55591
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparation or prerequisites

    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
     barely
    -0.06
    inth
    -0.06
    лÑĥÑĩ
    -0.06
    èŃ
    -0.06
    alis
    -0.06
    byn
    -0.06
     æļ
    -0.05
     donated
    -0.05
    tract
    -0.05
    alian
    -0.05
    POSITIVE LOGITS
     nhé
    0.07
    Threads
    0.07
    /stdc
    0.07
    leÅŁik
    0.07
    WAYS
    0.07
    UBLE
    0.07
    ourd
    0.07
    ToSelector
    0.07
    @if
    0.06
     PROCUREMENT
    0.06
    Activations Density 0.008%

    No Known Activations