© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77251
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics related to housing or living conditions

    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
    202
    -0.08
    SingleNode
    -0.07
    rieb
    -0.07
    ileged
    -0.07
    weit
    -0.07
    utow
    -0.07
    urous
    -0.07
    ázev
    -0.07
    igned
    -0.06
     announc
    -0.06
    POSITIVE LOGITS
    .cms
    0.07
     Erect
    0.07
    ãĤ¸
    0.07
    ลล
    0.06
    Í
    0.06
    INLINE
    0.06
    æĮĻ
    0.06
    ãn
    0.06
     patriot
    0.06
    simp
    0.06
    Activations Density 0.041%

    No Known Activations