© 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. 15-LLAMASCOPE-RES-131K
    6. 558
    Prev
    Next
    INDEX
    Explanations

    mentions of logging into accounts or systems

    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
    ierge
    -0.07
    asz
    -0.06
    .Alert
    -0.06
    achen
    -0.06
    igel
    -0.06
    渡
    -0.06
    udder
    -0.06
    itti
    -0.06
    é¡Į
    -0.06
    yth
    -0.06
    POSITIVE LOGITS
     into
    0.07
     onto
    0.07
    ncmp
    0.07
    irket
    0.06
    _into
    0.06
     боÑĢ
    0.06
     present
    0.06
    ansson
    0.06
    ë¹Ī
    0.06
    incorrect
    0.06
    Activations Density 0.007%

    No Known Activations