© 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. 83337
    Prev
    Next
    INDEX
    Explanations

    references to shopping and entertainment venues

    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
     tu
    -0.06
    YW
    -0.06
    uary
    -0.06
    chn
    -0.06
     intr
    -0.06
    ltk
    -0.06
    odal
    -0.06
    اک
    -0.06
    .Inventory
    -0.06
    ãĥŃãĥ³
    -0.06
    POSITIVE LOGITS
    arrant
    0.07
    alink
    0.07
    มาà¸ģมาย
    0.07
    ijľ
    0.07
    bung
    0.07
    brands
    0.07
     eater
    0.07
    oland
    0.06
     concerts
    0.06
     먹
    0.06
    Activations Density 0.019%

    No Known Activations