© 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. 56197
    Prev
    Next
    INDEX
    Explanations

    email addresses and related terms for communication

    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
    lider
    -0.07
    áš
    -0.06
    ceph
    -0.06
    rone
    -0.06
     Porter
    -0.06
    Enlarge
    -0.06
    ivi
    -0.06
    ôm
    -0.06
    877
    -0.06
     Wenger
    -0.06
    POSITIVE LOGITS
    ahoo
    0.10
    hotmail
    0.10
     gmail
    0.10
     Gmail
    0.10
    gmail
    0.09
    .gmail
    0.09
     yahoo
    0.09
    yahoo
    0.09
     domains
    0.09
     domain
    0.08
    Activations Density 0.064%

    No Known Activations