© 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. 60950
    Prev
    Next
    INDEX
    Explanations

    numerous instances of the word "the."

    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
    onian
    -0.07
    ulen
    -0.07
    redo
    -0.06
    ún
    -0.06
    imore
    -0.06
    baum
    -0.06
    æ£
    -0.06
    minster
    -0.06
    abra
    -0.06
    StackSize
    -0.06
    POSITIVE LOGITS
     United
    0.07
    ssid
    0.07
    ss
    0.07
    á»ĭnh
    0.07
    庫
    0.07
    ivery
    0.07
    ADR
    0.06
     Spoj
    0.06
    oids
    0.06
    %C
    0.06
    Activations Density 0.004%

    No Known Activations