© 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. 22-LLAMASCOPE-RES-131K
    6. 3879
    Prev
    Next
    INDEX
    Explanations

    recurring character names or titles in a narrative context

    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
    amus
    -0.08
    ento
    -0.08
    rement
    -0.07
    akash
    -0.07
    @qq
    -0.07
    agh
    -0.07
    tain
    -0.07
    atore
    -0.07
    bakan
    -0.07
    onom
    -0.07
    POSITIVE LOGITS
    olla
    0.10
    /live
    0.06
    ube
    0.06
     La
    0.06
     Bolt
    0.06
    ettes
    0.06
    779
    0.06
    ayette
    0.05
     Py
    0.05
     strict
    0.05
    Activations Density 0.001%

    No Known Activations