© 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. 125625
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shop" in various forms

    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
    ilm
    -0.07
     Bes
    -0.07
     Barcl
    -0.06
    ends
    -0.06
    lass
    -0.06
    ices
    -0.06
     bes
    -0.06
    ces
    -0.06
    Insets
    -0.06
    aver
    -0.06
    POSITIVE LOGITS
    menin
    0.07
    edList
    0.07
    EPHIR
    0.06
    mnop
    0.06
    ainen
    0.06
    Cog
    0.06
    reten
    0.06
    Łèĥ½
    0.06
    avid
    0.06
    avi
    0.06
    Activations Density 0.002%

    No Known Activations