© 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. 15-LLAMASCOPE-RES-131K
    11. 103665
    Prev
    Next
    INDEX
    Explanations

    locations and affiliations related to various individuals mentioned in the text

    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
    tual
    -0.07
    vie
    -0.07
    iland
    -0.07
    alore
    -0.07
    ünchen
    -0.07
    .REQUEST
    -0.07
    ruba
    -0.07
     haus
    -0.07
     пож
    -0.07
    als
    -0.07
    POSITIVE LOGITS
     Obr
    0.06
     intern
    0.06
     “
    0.06
     ger
    0.06
     van
    0.06
     Oswald
    0.06
     def
    0.05
     Ir
    0.05
     b
    0.05
     Downing
    0.05
    Activations Density 0.496%

    No Known Activations