© 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. 56124
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving or providing experiences or benefits

    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
     Roose
    -0.07
    ìĪĺìĿĺ
    -0.07
    _DYNAMIC
    -0.06
    ê°ľìĿĺ
    -0.06
    atego
    -0.06
    285
    -0.06
    ôi
    -0.06
    &e
    -0.06
    Ñģим
    -0.06
    inned
    -0.06
    POSITIVE LOGITS
     Ñģобой
    0.11
     itself
    0.10
     results
    0.08
     differently
    0.06
    results
    0.06
    568
    0.06
     Matth
    0.06
    ankind
    0.06
     RESULTS
    0.06
     ÑģобоÑİ
    0.06
    Activations Density 0.066%

    No Known Activations