© 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. 5-LLAMASCOPE-RES-131K
    11. 125953
    Prev
    Next
    INDEX
    Explanations

    words related to apartments and living spaces

    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
    691
    -0.07
    ARRANT
    -0.07
    eyen
    -0.07
    anou
    -0.07
    ÙħÙĪÙĦ
    -0.06
    алов
    -0.06
    ivec
    -0.06
    ť
    -0.06
    /upload
    -0.06
    rott
    -0.06
    POSITIVE LOGITS
    igraph
    0.06
    lia
    0.06
    ses
    0.06
    ampoline
    0.06
    .prompt
    0.06
     Basil
    0.06
    prompt
    0.06
    etz
    0.05
     Cly
    0.05
    _INITIALIZER
    0.05
    Activations Density 0.000%

    No Known Activations