© 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. 15-LLAMASCOPE-RES-131K
    11. 88566
    Prev
    Next
    INDEX
    Explanations

    specific numeric timestamps or versioning information

    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
    egas
    -0.08
    ÑģÑĥÑĤ
    -0.08
    iram
    -0.08
    EXPR
    -0.07
    ÏĢλα
    -0.07
    åŃĺäºİ
    -0.07
    uos
    -0.07
    regn
    -0.07
    iá»ĥu
    -0.07
    даÑĤ
    -0.06
    POSITIVE LOGITS
     ton
    0.06
     Ton
    0.06
    ton
    0.06
    ached
    0.06
     Dough
    0.06
    817
    0.06
     Tender
    0.06
    -ton
    0.05
    -
    0.05
    ses
    0.05
    Activations Density 0.001%

    No Known Activations