© 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. 57324
    Prev
    Next
    INDEX
    Explanations

    phrases related to assumptions and expectations

    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
    repid
    -0.07
    unden
    -0.07
    ORK
    -0.07
    vester
    -0.06
     eg
    -0.06
    ork
    -0.06
    strand
    -0.06
    eyen
    -0.06
    adla
    -0.06
    اÙģت
    -0.06
    POSITIVE LOGITS
     thus
    0.16
     böyle
    0.15
    è¿Ļæł·
    0.15
    è¿Ļç§į
    0.14
    è¿Ļæł·çļĦ
    0.14
     such
    0.14
    å¦ĤæѤ
    0.14
     ÑĤаким
    0.14
    è¿Ļä¹Ī
    0.13
     ìĿ´ëłĩê²Į
    0.13
    Activations Density 0.144%

    No Known Activations