© 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. 17-LLAMASCOPE-RES-131K
    11. 75359
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal opinions and emotions

    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
    esel
    -0.08
    ฤ
    -0.08
     ÄĮer
    -0.08
    errupted
    -0.08
    occan
    -0.07
    senal
    -0.07
    .nlm
    -0.07
    ModelError
    -0.07
    Ư
    -0.07
    uchos
    -0.07
    POSITIVE LOGITS
     miss
    0.07
     Meh
    0.06
     questioning
    0.06
     view
    0.06
     dis
    0.06
    esk
    0.06
     bail
    0.06
     indifference
    0.06
    view
    0.06
    dis
    0.06
    Activations Density 0.051%

    No Known Activations