© 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. 77162
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Brandon."

    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
    ÙĪاÙĩ
    -0.08
    _DELTA
    -0.07
    ystems
    -0.07
    dür
    -0.07
    enties
    -0.07
    IES
    -0.07
    aná
    -0.07
    oog
    -0.07
    viron
    -0.07
    ters
    -0.07
    POSITIVE LOGITS
    ake
    0.08
    iller
    0.07
    al
    0.07
    leur
    0.06
    naire
    0.06
    idd
    0.06
    Æ¡
    0.06
    iana
    0.06
    è¯Ŀ
    0.06
    ism
    0.06
    Activations Density 0.002%

    No Known Activations