© 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 EvalsExportsinterp-engineNEWAPI 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. 27395
    Prev
    Next
    INDEX
    Explanations

    conditional statements and their structures

    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
     Dixon
    -0.07
     Prev
    -0.07
    wat
    -0.07
     molec
    -0.06
    ë§Ŀ
    -0.06
     Either
    -0.06
    ixon
    -0.06
    Either
    -0.06
    íĦ¸
    -0.06
    (strict
    -0.06
    POSITIVE LOGITS
    acher
    0.07
    ipel
    0.06
    806
    0.06
    vrier
    0.06
    ekk
    0.06
    IVEN
    0.06
    ÑĩиÑģ
    0.06
    968
    0.06
    주ìĿĺ
    0.06
    839
    0.06
    Activations Density 0.020%

    No Known Activations