© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106308
    Prev
    Next
    INDEX
    Explanations

    references to Jewish subjects or themes

    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
    hong
    -0.07
    alach
    -0.07
     litter
    -0.06
    úc
    -0.06
    allel
    -0.06
     fl
    -0.06
    stal
    -0.06
     Crawford
    -0.06
    udes
    -0.06
    rooms
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥ©
    0.07
    dbc
    0.07
    -widgets
    0.06
    aci
    0.06
     Fist
    0.06
    座
    0.06
    iVar
    0.06
    ÙħÙĬÙĦ
    0.06
    ibar
    0.06
    ãĥ£
    0.06
    Activations Density 0.001%

    No Known Activations