© 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. 15-LLAMASCOPE-RES-131K
    11. 27334
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions or attitudes towards others

    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
    abled
    -0.06
    Injector
    -0.06
    redients
    -0.06
    odzi
    -0.06
    .tie
    -0.06
    istrate
    -0.06
    WithEmail
    -0.06
    odnÃŃ
    -0.06
    oningen
    -0.06
    Å¡nÃŃ
    -0.06
    POSITIVE LOGITS
    _sdk
    0.07
    ez
    0.06
    uple
    0.06
     Morr
    0.06
    erm
    0.06
    ahn
    0.06
    imagen
    0.06
    formulario
    0.06
    GLOBALS
    0.06
    еле
    0.06
    Activations Density 0.049%

    No Known Activations