© 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. 17-LLAMASCOPE-RES-131K
    6. 129337
    Prev
    Next
    INDEX
    Explanations

    numerical data related to participants, attendees, or quantities in events

    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
    baugh
    -0.08
    onda
    -0.07
     biting
    -0.06
    798
    -0.06
    æĶ
    -0.06
     Kash
    -0.06
    :///
    -0.06
    378
    -0.06
     anywhere
    -0.06
    dba
    -0.06
    POSITIVE LOGITS
     individual
    0.08
     BoxFit
    0.07
     pieces
    0.07
    las
    0.07
    iazza
    0.06
    ertino
    0.06
    ono
    0.06
    oust
    0.06
    ahl
    0.06
    utes
    0.06
    Activations Density 0.016%

    No Known Activations