© 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. 105948
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about residential 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
     uch
    -0.07
     Bedrooms
    -0.06
     Americas
    -0.06
     Chain
    -0.06
     insight
    -0.06
    abei
    -0.06
    chain
    -0.06
     bedrooms
    -0.06
    APH
    -0.06
    å¯Ŀ
    -0.06
    POSITIVE LOGITS
    orra
    0.08
     central
    0.07
    udas
    0.07
     uten
    0.07
    central
    0.07
     wash
    0.07
     washer
    0.07
    -navbar
    0.06
     minY
    0.06
    oly
    0.06
    Activations Density 0.019%

    No Known Activations