© 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. 9-LLAMASCOPE-RES-131K
    11. 94765
    Prev
    Next
    INDEX
    Explanations

    terms related to baking and leavening agents

    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
    ide
    -0.07
    uin
    -0.07
    omy
    -0.06
    lah
    -0.06
    adf
    -0.06
    ģµ
    -0.06
    ep
    -0.06
    usercontent
    -0.06
     ########################################################################
    -0.06
    furt
    -0.06
    POSITIVE LOGITS
    chwitz
    0.06
     Angiospermae
    0.06
    nis
    0.06
    lose
    0.06
     Stam
    0.05
     chicas
    0.05
     hung
    0.05
    okol
    0.05
    Ñıж
    0.05
    mlink
    0.05
    Activations Density 0.005%

    No Known Activations