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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125980
    Prev
    Next
    INDEX
    Explanations

    terms related to shopping and commercial activities

    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
    gii
    -0.06
     Mall
    -0.06
     designation
    -0.06
    åı·
    -0.06
    üf
    -0.06
     links
    -0.06
     poll
    -0.06
    ague
    -0.05
     Pam
    -0.05
    cheng
    -0.05
    POSITIVE LOGITS
    ÑĢÑĸп
    0.07
    ui
    0.07
    iken
    0.07
    PrivateKey
    0.07
    hoe
    0.07
    ,cp
    0.07
    jez
    0.07
    .getOutputStream
    0.07
    ei
    0.06
    να
    0.06
    Activations Density 0.042%

    No Known Activations