© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 119812
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "common" in various contexts

    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
    ourke
    -0.06
    è¹
    -0.06
     cooperative
    -0.06
     Cooperative
    -0.06
     susp
    -0.06
    ffa
    -0.06
     cloth
    -0.06
    vs
    -0.05
    &E
    -0.05
    quiv
    -0.05
    POSITIVE LOGITS
    TEE
    0.07
    UILayout
    0.07
    zed
    0.07
    opic
    0.07
    =YES
    0.07
    æŀļ
    0.07
    appendChild
    0.07
    adro
    0.07
    ONTAL
    0.07
    ERVED
    0.07
    Activations Density 0.003%

    No Known Activations