© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 233
    Prev
    Next
    INDEX
    Explanations

    instances of interaction with various subjects or entities

    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
    uraa
    -0.08
    KeySpec
    -0.07
    Ĥ¬
    -0.07
    Lng
    -0.07
    ilig
    -0.07
    otu
    -0.07
    ä
    -0.07
    ará
    -0.06
    urf
    -0.06
    _EXEC
    -0.06
    POSITIVE LOGITS
    å¼ı
    0.06
     interact
    0.06
    uality
    0.06
    lez
    0.06
    ephir
    0.06
    919
    0.06
     Voyage
    0.06
    üh
    0.06
    imore
    0.06
     Via
    0.06
    Activations Density 0.023%

    No Known Activations