© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77245
    Prev
    Next
    INDEX
    Explanations

    opening and closing tags in XML or HTML formatted documents

    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
    thers
    -0.07
    tres
    -0.07
    stm
    -0.07
    owie
    -0.07
    ieu
    -0.07
    trie
    -0.07
    ie
    -0.06
    innie
    -0.06
     treff
    -0.06
    .OR
    -0.06
    POSITIVE LOGITS
    uja
    0.06
    ĥn
    0.06
    ackbar
    0.06
     Benson
    0.06
     CharSet
    0.06
    ihat
    0.06
    çľ
    0.05
    actionDate
    0.05
    ¤¤
    0.05
     impro
    0.05
    Activations Density 0.004%

    No Known Activations