© 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. 22-LLAMASCOPE-RES-131K
    6. 3608
    Prev
    Next
    INDEX
    Explanations

    numerical references and metadata

    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
    ayar
    -0.07
     window
    -0.06
    ston
    -0.06
    ť
    -0.06
    izio
    -0.06
    ickey
    -0.06
    амеÑĤ
    -0.06
    apter
    -0.06
     enterprise
    -0.06
    etri
    -0.06
    POSITIVE LOGITS
    iele
    0.07
     Jeho
    0.07
     counselor
    0.06
    irler
    0.06
    enschaft
    0.06
    dyby
    0.06
     pie
    0.06
     Awake
    0.06
    foon
    0.06
    jer
    0.06
    Activations Density 0.000%

    No Known Activations