© 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. 70779
    Prev
    Next
    INDEX
    Explanations

    phrases related to information and its reliability

    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
    pery
    -0.08
    enga
    -0.08
    atters
    -0.08
    info
    -0.07
    iper
    -0.07
    uteur
    -0.07
     okol
    -0.07
     information
    -0.07
    cour
    -0.06
    INO
    -0.06
    POSITIVE LOGITS
     exec
    0.07
    íĥģ
    0.07
    اÙĦÙģ
    0.06
    zd
    0.06
    .Func
    0.06
    .nlm
    0.06
    646
    0.06
    ÑĢд
    0.06
     pros
    0.06
    urations
    0.06
    Activations Density 0.012%

    No Known Activations