© 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. 94095
    Prev
    Next
    INDEX
    Explanations

    concepts related to heritage preservation and museum functions

    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
    itta
    -0.07
    ensi
    -0.07
    âķĹ
    -0.07
    iT
    -0.07
    orman
    -0.07
    .INSTANCE
    -0.07
    lama
    -0.07
     Euras
    -0.07
    chet
    -0.07
    grese
    -0.06
    POSITIVE LOGITS
     museum
    0.14
     Museum
    0.12
     museums
    0.11
     visitor
    0.10
    useum
    0.10
     Visitor
    0.10
     muse
    0.09
     Muse
    0.09
     visitors
    0.09
    åįļçī©
    0.08
    Activations Density 0.019%

    No Known Activations