© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128989
    Prev
    Next
    INDEX
    Explanations

    definitions and concepts related to mathematical graph properties

    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
     Classic
    -0.06
     funnel
    -0.06
    vil
    -0.06
    acha
    -0.06
     -
    -0.06
     lump
    -0.06
     classic
    -0.05
     trick
    -0.05
     or
    -0.05
     stere
    -0.05
    POSITIVE LOGITS
     definition
    0.12
    Definition
    0.12
     Definition
    0.12
    -definition
    0.11
    Definitions
    0.11
    definition
    0.11
     Definitions
    0.10
     definitions
    0.10
    å®ļä¹ī
    0.09
    definitions
    0.09
    Activations Density 0.078%

    No Known Activations