© 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. 29420
    Prev
    Next
    INDEX
    Explanations

    terms expressing comparisons or similarities

    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
    iy
    -0.07
    idders
    -0.07
    амп
    -0.06
    еком
    -0.06
    ãĥªãĥ¼
    -0.06
    ãĥ³ãĥģ
    -0.06
    oras
    -0.06
    quer
    -0.06
    ÑĤÑĢа
    -0.06
    aler
    -0.06
    POSITIVE LOGITS
    HashCode
    0.07
    isque
    0.06
    LBL
    0.06
    utedString
    0.06
     ours
    0.06
    ocz
    0.06
    -haspopup
    0.06
     Ans
    0.06
     notamment
    0.06
     denen
    0.06
    Activations Density 0.026%

    No Known Activations