© 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. 15
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to user interface programming and web development

    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
    ensi
    -0.07
    orthand
    -0.07
    edio
    -0.07
    AnimationFrame
    -0.07
    orch
    -0.06
    ViewChild
    -0.06
    leftright
    -0.06
    alus
    -0.06
    PRETTY
    -0.06
    assin
    -0.06
    POSITIVE LOGITS
     instead
    0.06
     via
    0.06
    erken
    0.06
    Via
    0.06
    arry
    0.06
     Via
    0.06
    ursos
    0.06
    axter
    0.06
    via
    0.06
    ä¿
    0.06
    Activations Density 0.026%

    No Known Activations